MPI-INF Logo
Homepage

Contact

Firstname Lastname

Dr. Marc Habermann

Max-Planck-Institut für Informatik
Department 6: Visual Computing and Artificial Intelligence
 position: Research Group Leader / Head of the Real Virtual Lab
 office: Campus E1 4, Room 216
Saarland Informatics Campus
66123 Saarbrücken
Germany
 email: mhaberma@mpi-inf.mpg.de
 phone: +49 681 9325-4507
 fax: +49 681 9325-4099
Google Scholar

Research Interests

I am the research group leader of the Graphics and Vision for Digital Humans group at the Max Planck Institute for Informatics. My research interests lie in the field of Computer Vision, Computer Graphics, and Machine Learning. In particular, my work focuses on real-time human performance capture from single RGB videos, physical plausibility of the surface deformations and the human motion, photo-realistic animation synthesis, and learning generative 3D human characters from video.

In summary, my research interests include (but are not limited to):
  • Computer Vision, Computer Graphics, Machine Learning
  • Human Performance Capture and Synthesis
  • Reconstruction of Non-Rigid Deformations from RGB Video
  • Neural Rendering
  • Motion Capture

Invited Talks

  • 2023-05-03 Digital Humans @ Saarland Informatics Campus Lecture Series [video]
  • 2022-07-11 Human Performance Capture and Synthesis @ Adobe [video]
  • 2021-09-28 Real-time Deep Dynamic Characters @ Google Zuerich [video]
  • 2020-10-29 DeepCap @ Computer Vision Reading Group EPFL [video]

Pre-prints

Relightable Neural Actor with Intrinsic Decomposition and Pose Control

Diogo Luvizon   Vladislav Golyanik   Adam Kortylewski   Marc Habermann   Christian Theobalt  

arxiv 2023

Abstract
Creating a controllable and relightable digital avatar from multi-view video with fixed illumination is a very challenging problem since humans are highly articulated, creating pose-dependent appearance effects, and skin as well as clothing require space-varying BRDF modeling. Existing works on creating animatible avatars either to not focus on relighting at all, require controlled illumination setups, or try to recover a relightable avatar from very low cost setups, i.e. a single RGB video, at the cost of severely limited result quality, e.g. shadows not even being modeled. To address this, we propose Relightable Neural Actor, a new video-based method for learning a pose-driven neural human model that can be relighted, allows appearance editing, and models pose-dependent effects such as wrinkles and self-shadows. Importantly, for training, our method solely requires a multi-view recording of the human under a known, but static lighting condition. To tackle this challenging problem, we leverage an implicit geometry representation of the actor with a drivable density field that models pose-dependent deformations and derive a dynamic mapping between 3D and UV spaces, where normal, visibility, and materials are effectively encoded. To evaluate our approach in real-world scenarios, we collect a new dataset with four identities recorded under different light conditions, indoors and outdoors, providing the first benchmark of its kind for human relighting, and demonstrating state-of-the-art relighting results for novel human poses.

[pdf], [video], [project page], [arxiv]



Surf-D: High-Quality Surface Generation for Arbitrary Topologies using Diffusion Models

Zhengming Yu   Zhiyang Dou   Xiaoxiao Long   Cheng Lin   Zekun Li   Yuan Liu   Norman Mueller   Taku Komura   Marc Habermann   Christian Theobalt   Xin Li   Wenping Wang  

arxiv 2023

Abstract
We present Surf-D, a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies using Diffusion models. Specifically, we adopt Unsigned Distance Field (UDF) as the surface representation, as it excels in handling arbitrary topologies, enabling the generation of complex shapes. While the prior methods explored shape generation with different representations, they suffer from limited topologies and geometry details. Moreover, it's non-trivial to directly extend prior diffusion models to UDF because they lack spatial continuity due to the discrete volume structure. However, UDF requires accurate gradients for mesh extraction and learning. To tackle the issues, we first leverage a point-based auto-encoder to learn a compact latent space, which supports gradient querying for any input point through differentiation to effectively capture intricate geometry at a high resolution. Since the learning difficulty for various shapes can differ, a curriculum learning strategy is employed to efficiently embed various surfaces, enhancing the whole embedding process. With pretrained shape latent space, we employ a latent diffusion model to acquire the distribution of various shapes. Our approach demonstrates superior performance in shape generation across multiple modalities and conducts extensive experiments in unconditional generation, category conditional generation, 3D reconstruction from images, and text-to-shape tasks.

[pdf], [video], [project page], [arxiv]



NeuralClothSim: Neural Deformation Fields Meet the Kirchhoff-Love Thin Shell Theory

Navami Kairanda   Marc Habermann   Christian Theobalt   Vladislav Golyanik  

arxiv 2023

Abstract
Cloth simulation is an extensively studied problem, with a plethora of solutions available in computer graphics literature. Existing cloth simulators produce realistic cloth deformations that obey different types of boundary conditions. Nevertheless, their operational principle remains limited in several ways: They operate on explicit surface representations with a fixed spatial resolution, perform a series of discretised updates (which bounds their temporal resolution), and require comparably large amounts of storage. Moreover, back-propagating gradients through the existing solvers is often not straightforward, which poses additional challenges when integrating them into modern neural architectures. In response to the limitations mentioned above, this paper takes a fundamentally different perspective on physically-plausible cloth simulation and re-thinks this long-standing problem: We propose NeuralClothSim, i.e., a new cloth simulation approach using thin shells, in which surface evolution is encoded in neural network weights. Our memory-efficient and differentiable solver operates on a new continuous coordinate-based representation of dynamic surfaces, i.e., neural deformation fields (NDFs); it supervises NDF evolution with the rules of the non-linear Kirchhoff-Love shell theory. NDFs are adaptive in the sense that they 1) allocate their capacity to the deformation details as the latter arise during the cloth evolution and 2) allow surface state queries at arbitrary spatial and temporal resolutions without retraining. We show how to train our NeuralClothSim solver while imposing hard boundary conditions and demonstrate multiple applications, such as material interpolation and simulation editing. The experimental results highlight the effectiveness of our formulation and its potential impact.

[pdf], [video], [project page], [arxiv]


Publications

ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering

Haokai Pang   Heming Zhu   Adam Kortylewski   Christian Theobalt   Marc Habermann  

CVPR 2024

Abstract
Real-time rendering of photorealistic and controllable human avatars stands as a cornerstone in Computer Vision and Graphics. While recent advances in neural implicit rendering have unlocked unprecedented photorealism for digital avatars, real-time performance has mostly been demonstrated for static scenes only. To address this, we propose ASH, an Animatable Gaussian Splatting approach for photorealistic rendering of dynamic Humans in real time. We parameterize the clothed human as animatable 3D Gaussians, which can be efficiently splatted into image space to generate the final rendering. However, naively learning the Gaussian parameters in 3D space poses a severe challenge in terms of compute. Instead, we attach the Gaussians onto a deformable character model, and learn their parameters in 2D texture space, which allows leveraging efficient 2D convolutional architectures that easily scale with the required number of Gaussians. We benchmark ASH with competing methods on pose-controllable avatars, demonstrating that our method outperforms existing real-time methods by a large margin and shows comparable or even better results than offline methods.

[pdf], [video], [project page], [arxiv]



Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras Rendering

Ashwath Shetty   Marc Habermann   Guoxing Sun   Diogo Luvizon   Vladislav Golyanik   Christian Theobalt  

CVPR 2024

Abstract
We present the first approach to render highly realistic free-viewpoint videos of a human actor in general apparel, from sparse multi-view recording to display, in real-time at an unprecedented 4K resolution. At inference, our method only requires four camera views of the moving actor and the respective 3D skeletal pose. It handles actors in wide clothing, and reproduces even fine-scale dynamic detail, e.g. clothing wrinkles, face expressions, and hand gestures. At training time, our learning-based approach expects dense multi-view video and a rigged static surface scan of the actor. Our method comprises three main stages. Stage 1 is a skeleton-driven neural approach for high-quality capture of the detailed dynamic mesh geometry. Stage 2 is a novel solution to create a view-dependent texture using four test-time camera views as input. Finally, stage 3 comprises a new image-based refinement network rendering the final 4K image given the output from the previous stages. Our approach establishes a new benchmark for real-time rendering resolution and quality using sparse input camera views, unlocking possibilities for immersive telepresence.

[pdf], [video], [project page], [arxiv]



VINECS: Video-based Neural Character Skinning

Zhouyingcheng Liao   Vladislav Golyanik   Marc Habermann   Christian Theobalt  

CVPR 2024

Abstract
Rigging and skinning clothed human avatars is a challenging task and traditionally requires a lot of manual work and expertise. Recent methods addressing it either generalize across different characters or focus on capturing the dynamics of a single character observed under different pose configurations. However, the former methods typically predict solely static skinning weights, which perform poorly for highly articulated poses, and the latter ones either require dense 3D character scans in different poses or cannot generate an explicit mesh with vertex correspondence over time. To address these challenges, we propose a fully automated approach for creating a fully rigged character with pose-dependent skinning weights, which can be solely learned from multi-view video. Therefore, we first acquire a rigged template, which is then statically skinned. Next, a coordinate-based MLP learns a skinning weights field parameterized over the position in a canonical pose space and the respective pose. Moreover, we introduce our pose- and view-dependent appearance field allowing us to differentiably render and supervise the posed mesh using multi-view imagery. We show that our approach outperforms state-of-the-art while not relying on dense 4D scans.

[pdf], [video], [project page], [arxiv]



Wonder3D: Single Image to 3D using Cross-Domain Diffusion

Xiaoxiao Long   Yuan-Chen Guo   Cheng Lin   Yuan Liu   Zhiyang Dou   Lingjie Liu   Yuexin Ma   Song-Hai Zhang   Marc Habermann   Christian Theobalt   Wenping Wang  

CVPR 2024

Abstract
In this work, we introduce Wonder3D, a novel method for efficiently generating high-fidelity textured meshes from single-view images. Recent methods based on Score Dis- tillation Sampling (SDS) have shown the potential to re- cover 3D geometry from 2D diffusion priors, but they typ- ically suffer from time-consuming per-shape optimization and inconsistent geometry. In contrast, certain works di- rectly produce 3D information via fast network inferences, but their results are often of low quality and lack geomet- ric details. To holistically improve the quality, consistency, and efficiency of single-view reconstruction tasks, we pro- pose a cross-domain diffusion model that generates multi- view normal maps and the corresponding color images. To ensure the consistency of generation, we employ a multi- view cross-domain attention mechanism that facilitates in- formation exchange across views and modalities. Lastly, we introduce a geometry-aware normal fusion algorithm that extracts high-quality surfaces from the multi-view 2D rep- resentations. Our extensive evaluations demonstrate that our method achieves high-quality reconstruction results, ro- bust generalization, and good efficiency compared to prior works.

[pdf], [video], [project page], [arxiv]



ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis

Muhammad Hamza Mughal   Rishabh Dabral   Ikhsanul Habibie   Lucia Donatelli   Marc Habermann   Christian Theobalt  

CVPR 2024

Abstract
Gestures play a key role in human communication. Recent methods for co-speech gesture generation, while managing to generate beat-aligned motions, struggle generating gestures that are semantically aligned with the utterance. Compared to beat gestures that align naturally to the audio signal, generating semantically coherent gestures require modeling the complex interactions between the words, their meaning and the human motion. Therefore, we present ConvoFusion, a diffusion-based approach for multi-modal gesture synthesis, which can not only generate gestures based on multi-modal speech inputs, but can also facilitate controllability in gesture synthesis. Our method proposes two guidance objectives that allow the users to modulate the impact of different conditioning modalities (e.g. audio vs text) as well as to choose certain words to be emphasized during gesturing. Our method is versatile in that it can be trained either for generating monologue gestures or even the conversational gestures. To further advance the research on multi-party interactive gestures, the DND Group Gesture dataset is released, which contains 6 hours of gesture data showing 5 people interacting with one another. We compare our method with several recent works and demonstrate effectiveness of our method on a variety of tasks.

Details coming soon!



ROAM: Robust and Object-aware Motion Generation using Neural Pose Descriptors

Wanyue Zhang   Rishabh Dabral   Thomas Leimkühler   Vladislav Golyanik   Marc Habermann   Christian Theobalt  

3DV 2024

Abstract
Existing automatic approaches for 3D virtual character motion synthesis supporting scene interactions do not generalise well to new objects outside training distributions, even when trained on extensive motion capture datasets with diverse objects and annotated interactions. This paper addresses this limitation and shows that robustness and generalisation to novel scene objects in 3D object-aware character synthesis can be achieved by training a motion model with as few as one reference object. We leverage an implicit feature representation trained on object-only datasets, which encodes an SE(3)-equivariant descriptor field around the object. Given an unseen object and a reference pose-object pair, we optimise for the object-aware pose that is closest in the feature space to the reference pose.Finally, we use l-NSM, i.e. our motion generation model that is trained to seamlessly transition from locomotion to object interaction with the proposed bidirectional pose blending scheme. Through comprehensive numerical comparisons to state-of-the-art methods and in a user study, we demonstrate substantial improvements in 3D virtual character motion and interaction quality and robustness to scenarios with unseen objects.

[pdf], [video], [project page], [arxiv]


2023



DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis

Youngjoong Kwon   Lingjie Liu   Henry Fuchs   Marc Habermann   Christian Theobalt  

Neurips 2023

Abstract
Generating controllable and photorealistic digital human avatars is a long-standing and important problem in Vision and Graphics. Recent methods have shown great progress in terms of either photorealism or inference speed while the combination of the two desired properties still remains unsolved. To this end, we propose a novel method, called DELIFFAS, which parameterizes the appearance of the human as a surface light field that is attached to a controllable and deforming human mesh model. At the core, we represent the light field around the human with a deformable two-surface parameterization, which enables fast and accurate inference of the human appearance. This allows perceptual supervision on the full image compared to previous approaches that could only supervise individual pixels or small patches due to their slow runtime. Our carefully designed human representation and supervision strategy leads to state-of-the-art synthesis results and inference time.

[pdf], [video], [project page], [arxiv]



Diffusion Posterior Illumination for Ambiguity-aware Inverse Rendering

Linjie Lyu   Ayush Tewari   Marc Habermann   Shunsuke Saito   Michael Zollhoefer  
Thomas Leimkühler   Christian Theobalt  

Siggraph Asia 2023

Abstract
Inverse rendering, the process of inferring scene properties from images, is a challenging inverse problem. The task is ill-posed, as many different scene configurations can give rise to the same image. Most existing solutions incorporate priors into the inverse-rendering pipeline to encourage plausible solutions, but they do not consider the inherent ambiguities and the multi-modal distribution of possible decompositions. In this work, we propose a novel scheme that integrates a denoising diffusion probabilistic model pre-trained on natural illumination maps into an optimization framework involving a differentiable path tracer. The proposed method allows sampling from combinations of illumination and spatially-varying surface materials that are, both, natural and explain the image observations. We further conduct an extensive comparative study of different priors on illumi- nation used in previous work on inverse rendering. Our method excels in recovering materials and producing highly realistic and diverse environment map samples that faithfully explain the illumination of the input images.

[pdf], [video], [project page], [arxiv]



Discovering Fatigued Movements for Virtual Character Animation

Noshaba Cheema   Rui Xu   Nam Hee Kim   Perttu Hämäläinen   Vladislav Golyanik   Marc Habermann   Christian Theobalt   Philipp Slusallek  

Siggraph Asia 2023

Abstract
Virtual character animation and movement synthesis have advanced rapidly during recent years, especially through a combination of extensive motion capture datasets and machine learning. A remaining challenge is interactively simulating characters that fatigue when performing extended motions, which is indispensable for the realism of generated animations. However, capturing such movements is problematic, as performing movements like backflips with fatigued variations up to exhaustion raises capture cost and risk of injury. Surprisingly, little research has been done on faithful fatigue modeling. To address this, we propose a deep reinforcement learning-based approach, which—for the first time in literature—generates control policies for full-body physically simulated agents aware of cumulative fatigue. For this, we first leverage Generative Adversarial Imitation Learning (GAIL) to learn an expert policy for the skill; Second, we learn a fatigue policy by limiting the generated constant torque bounds based on endurance time to non-linear, state- and time-dependent limits in the joint-actuation space using a Three-Compartment Controller (3CC) model. Our results demonstrate that agents can adapt to different fatigue and rest rates interactively, and discover realistic recovery strategies without the need for any captured data of fatigued movements.

[pdf], [video], [project page], [arxiv]



LiveHand: Real-time and Photorealistic Neural Hand Rendering

Akshay Mundra   Mallikarjun B R   Jiayi Wang   Marc Habermann   Christian Theobalt  
Mohamed Elgharib  

ICCV 2023

Abstract
The human hand is the main medium through which we interact with our surroundings. Hence, its digitization is of uttermost importance, with direct applications in VR/AR, gaming, and media production amongst other areas. While there are several works modeling the geometry of hands, little attention has been paid to capturing photo-realistic appearance. Moreover, for applications in extended reality and gaming, real-time rendering is critical. We present the first neural- implicit approach to photo-realistically render hands in real-time. This is a challenging problem as hands are textured and undergo strong articulations with pose-dependent effects. However, we show that this aim is achievable through our carefully designed method. This includes training on a low- resolution rendering of a neural radiance field, together with a 3D-consistent super-resolution module and mesh-guided sampling and space canonicaliza- tion. We demonstrate a novel application of perceptual loss on the image space, which is critical for learning details accurately. We also show a live demo where we photo-realistically render the human hand in real-time for the first time, while also modeling pose- and view-dependent appearance effects. We ablate all our design choices and show that they optimize for rendering speed and quality.

[pdf], [video], [project page], [arxiv]



NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction

Yiming Wang   Qin Han   Marc Habermann   Kostas Daniilidis   Christian Theobalt  
Lingjie Liu  

ICCV 2023

Abstract
Recent methods for neural surface representation and rendering, for example NeuS, have demonstrated remarkably high-quality reconstruction of static scenes. However, the training of NeuS takes an extremely long time (8~hours), which makes it almost impossible to apply them to dynamic scenes with thousands of frames. We propose a fast neural surface reconstruction approach, called NeuS2, which achieves two orders of magnitude improvement in terms of acceleration without compromising reconstruction quality. To accelerate the training process, we integrate multi-resolution hash encodings into a neural surface representation and implement our whole algorithm in CUDA. We also present a lightweight calculation of second-order derivatives tailored to our networks (i.e., ReLU-based MLPs), which achieves a factor two speed up. To further stabilize training, a progressive learning strategy is proposed to optimize multi-resolution hash encodings from coarse to fine. In addition, we extend our method for reconstructing dynamic scenes with an incremental training strategy. Our experiments on various datasets demonstrate that NeuS2 significantly outperforms the state-of-the-arts in both surface reconstruction accuracy and training speed.

[pdf], [video], [project page], [arxiv]



HDHumans: A Hybrid Approach for High-fidelity Digital Humans

Marc Habermann   Lingjie Liu   Weipeng Xu   Gerard Pons-Moll   Michael Zollhoefer  
Christian Theobalt

SCA 2023 Best Paper Honorable Mention

Abstract
Photo-real digital human avatars are of enormous importance in graphics, as they enable immersive communication over the globe, improve gaming and entertainment experiences, and can be particularly beneficial for AR and VR settings. However, current avatar generation approaches either fall short in high-fidelity novel view synthesis, generalization to novel motions, reproduction of loose clothing, or they cannot render characters at the high resolution offered by modern displays. To this end, we propose HDHumans, which is the first method for HD human character synthesis that jointly produces an accurate and temporally coherent 3D deforming surface and highly photo-realistic images of arbitrary novel views and of motions not seen at training time. At the technical core, our method tightly integrates a classical deforming character template with neural radiance fields (NeRF). Our method is carefully designed to achieve a synergy between classical surface deformation and NeRF. First, the template guides the NeRF, which allows synthesizing novel views of a highly dynamic and articulated char- acter and even enables the synthesis of novel motions. Second, we also leverage the dense pointclouds resulting from NeRF to further improve the deforming surface via 3D-to-3D supervision. We outperform the state of the art quantitatively and qualitatively in terms of synthesis quality and resolution, as well as the quality of 3D surface reconstruction.

[pdf], [video], [project page], [arxiv]



EgoLocate: Real-time Motion Capture, Localization, and Mapping with Sparse Body-mounted Sensors

Xinyu Yi   Yuxiao Zhou   Marc Habermann   Vladislav Golyanik   Shaohua Pan   Christian Theobalt  
Feng Xu  

SIGGRAPH 2023

Abstract
Human and environment sensing are two important topics in Computer Vision and Graphics. Human motion is often captured by inertial sensors (left), while the environment is mostly reconstructed using cameras (right). We integrate the two techniques together in EgoLocate (middle), a system that simultaneously performs human motion capture (mocap), localization, and mapping in real time from sparse body-mounted sensors, including 6 inertial measurement units (IMUs) and a monocular phone camera. On one hand, inertial mocap suffers from large translation drift due to the lack of the global positioning signal. EgoLocate leverages image-based simultaneous localization and mapping (SLAM) techniques to locate the human in the reconstructed scene. On the other hand, SLAM often fails when the visual feature is poor. EgoLocate involves inertial mocap to provide a strong prior for the camera motion. Experiments show that localization, a key challenge for both two fields, is largely improved by our technique, compared with the state of the art of the two fields.

[pdf], [video], [project page], [arxiv], [code]



Unbiased 4D: Monocular 4D Reconstruction with a Neural Deformation Model

Erik C.M. Johnson   Marc Habermann   Soshi Shimada   Vladislav Golyanik   Christian Theobalt  

CVPR Workshop 2023

Abstract
Capturing general deforming scenes is crucial for many applications in computer graphics and vision, and it is especially challenging when only a monocular RGB video of the scene is available. Competing methods assume dense point tracks over the input views, 3D templates, large-scale training datasets, or only capture small-scale deformations. In stark contrast to those, our method makes none of these assumptions while significantly outperforming the previous state of the art in challenging scenarios. Moreover, our technique includes two new—in the context of non-rigid 3D reconstruction—components, i.e., 1) A coordinate-based and implicit neural representation for non-rigid scenes, which enables an unbiased reconstruction of dynamic scenes, and 2) A novel dynamic scene flow loss, which enables the reconstruction of larger deformations. Results on our new dataset, which will be made publicly available, demonstrate the clear improvement over the state of the art in terms of surface reconstruction accuracy and robustness to large deformations.

[pdf], [project page], [video], [arxiv]



State of the Art in Dense Monocular Non-Rigid 3D Reconstruction

Edith Tretschk   Navami Kairanda   Mallikarjun B R   Rishabh Dabral   Adam Kortylewski   Bernhard Egger   Marc Habermann   Pascal Fua   Christian Theobalt   Vladislav Golyanik  

Eurographics 2023 (STAR Report)

Abstract
3D reconstruction of deformable (or non-rigid) scenes from a set of monocular 2D image observations is a long-standing and actively researched area of computer vision and graphics. It is an ill-posed inverse problem, since—without additional prior assumptions—it permits infinitely many solutions leading to accurate projection to the input 2D images. Non-rigid reconstruction is a foundational building block for downstream applications like robotics, AR/VR, or visual content creation. The key advantage of using monocular cameras is their omnipresence and availability to the end users as well as their ease of use compared to more sophisticated camera set-ups such as stereo or multi-view systems. This survey focuses on state-of-the-art methods for dense non-rigid 3D reconstruction of various deformable objects and composite scenes from monocular videos or sets of monocular views. It reviews the fundamentals of 3D reconstruction and deformation modeling from 2D image observations. We then start from general methods—that handle arbitrary scenes and make only a few prior assumptions—and proceed towards techniques making stronger assumptions about the observed objects and types of deformations (e.g. human faces, bodies, hands, and animals). A significant part of this STAR is also devoted to classification and a high-level comparison of the methods, as well as an overview of the datasets for training and evaluation of the discussed techniques. We conclude by discussing open challenges in the field and the social aspects associated with the usage of the reviewed methods.

[pdf], [project page], [arxiv]



Scene-Aware 3D Multi-Human Motion Capture from a Single Camera

Diogo Luvizon   Marc Habermann   Vladislav Golyanik   Adam Kortylewski   Christian Theobalt  

Eurographics 2023

Abstract
In this work, we consider the problem of estimating the 3D position of multiple humans in a scene as well as their body shape and articulation from a single RGB video recorded with a static camera. In contrast to expensive marker-based or multi-view systems, our lightweight setup is ideal for private users as it enables an affordable 3D motion capture that is easy to install and does not require expert knowledge. To deal with this challenging setting, we leverage recent advances in computer vision using large-scale pre-trained models for a variety of modalities, including 2D body joints, joint angles, normalized disparity maps, and human segmentation masks. Thus, we introduce the first non-linear optimization-based approach that jointly solves for the absolute 3D position of each human, their articulated pose, their individual shapes as well as the scale of the scene. In particular, we estimate the scene depth and person unique scale from normalized disparity predictions using the 2D body joints and joint angles. Given the per-frame scene depth, we reconstruct a point-cloud of the static scene in 3D space. Finally, given the per-frame 3D estimates of the humans and scene point-cloud, we perform a space-time coherent optimization over the video to ensure temporal, spatial and physical plausibility. We evaluate our method on established multi-person 3D human pose benchmarks where we consistently outperform previous methods and we qualitatively demonstrate that our method is robust to in-the-wild conditions including challenging scenes with people of different sizes.

[pdf], [video], [project page], [arxiv]


2022



HiFECap: Monocular High-Fidelity and Expressive Capture of Human Performances

Yue Jiang   Marc Habermann   Vladislav Golyanik   Christian Theobalt  

BMVC 2022

Abstract
Monocular 3D human performance capture is indispensable for many applications in computer graphics and vision for enabling immersive experiences. However, detailed capture of humans requires tracking of multiple aspects, including the skeletal pose, the dynamic surface, which includes clothing, hand gestures as well as facial expressions. No existing monocular method allows joint tracking of all these components. To this end, we propose HiFECap, a new neural human performance capture approach, which simultaneously captures human pose, clothing, facial expression, and hands just from a single RGB video. We demonstrate that our proposed network architecture, the carefully designed training strategy, and the tight integration of parametric face and hand models to a template mesh enable the capture of all these individual aspects. Importantly, our method also captures high-frequency details, such as deforming wrinkles on the clothes, better than the previous works. Furthermore, we show that HiFECap outperforms the state-of-the-art human performance capture approaches qualitatively and quantitatively while for the first time capturing all aspects of the human.

[pdf], [video], [project page], [arxiv]



Neural Radiance Transfer Fields for Relightable Novel-view Synthesis with Global Illumination

Linjie Lyu   Ayush Tewari   Thomas Leimkühler   Marc Habermann   Christian Theobalt  

ECCV 2022 (Oral)

Abstract
Given a set of images of a scene, the re-rendering of this scene from novel views and lighting conditions is an important and challenging problem in Computer Vision and Graphics. On the one hand, most existing works in Computer Vision usually impose many assumptions regarding the image formation process, e.g. direct illumination and predefined materials, to make scene parameter estimation tractable. On the other hand, mature Computer Graphics tools allow modeling of complex photo-realistic light transport given all the scene parameters. Combining these approaches, we propose a method for scene relighting under novel views by learning a neural precomputed radiance transfer function, which implicitly handles global illumination effects using novel environment maps. Our method can be solely supervised on a set of real images of the scene under a single unknown lighting condition. To disambiguate the task during training, we tightly integrate a differentiable path tracer in the training process and propose a combination of a synthesized OLAT and a real image loss. Results show that the recovered disentanglement of scene parameters improves significantly over the current state of the art and, thus, also our re-rendering results are more realistic and accurate.

[pdf], [video], [project page], [arxiv], [code]



Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensors

Xinyu Yi   Yuxiao Zhou   Marc Habermann   Soshi Shimada   Vladislav Golyanik   Christian Theobalt  
Feng Xu  

CVPR 2022 Best paper candidate (1.6% of accepted papers)

Abstract
Motion capture from sparse inertial sensors has shown great potential compared to image-based approaches since occlusions do not lead to a reduced tracking quality and the recording space is not restricted to be within the viewing frustum of the camera. However, capturing the motion and global position only from a sparse set of inertial sensors is inherently ambiguous and challenging. In consequence, recent state-of-the-art methods can barely handle very long period motions, and unrealistic artifacts are common due to the unawareness of physical constraints. To this end, we present the first method which combines a neural kinematics estimator and a physics-aware motion optimizer to track body motions with only 6 inertial sensors. The kinematics module first regresses the motion status as a reference, and then the physics module refines the motion to satisfy the physical constraints. Experiments demonstrate a clear improvement over the state of the art in terms of capture accuracy, temporal stability, and physical correctness.

[pdf], [project page], [arxiv], [code]


2021



Real-time Human Performance Capture and Synthesis

Marc Habermann  

PhD Thesis 2021

Otto Hahn Medal 2022

Eurographics PhD Award 2022

DAGM MVTec Dissertation Award 2022

Abstract
Most of the images one finds in the media, such as on the Internet or in textbooks and magazines, contain humans as the main point of attention. Thus, there is an inherent necessity for industry, society, and private persons to be able to thoroughly analyze and synthesize the human-related content in these images. One aspect of this analysis and subject of this thesis is to infer the 3D pose and surface deformation, using only visual information, which is also known as human performance capture. This thesis proposes two monocular human performance capture methods, which for the first time allow the real-time capture of the dense deforming geometry as well as an unseen 3D accuracy for pose and surface deformations. At the technical core, this work introduces novel GPU-based and data-parallel optimization strategies in conjunction with other algorithmic design choices that are all geared towards real-time performance at high accuracy. Moreover, this thesis presents a new weakly supervised multi-view training strategy combined with a fully differentiable character representation that shows superior 3D accuracy. However, there is more to human-related Computer Vision than only the analysis of people in images. It is equally important to synthesize new images of humans in unseen poses and also from camera viewpoints that have not been observed in the real world. To this end, this thesis presents a method and ongoing work on character synthesis, which allow the synthesis of controllable photoreal characters that achieve motion- and view-dependent appearance effects as well as 3D consistency and which run in real time. This is technically achieved by a novel coarse-to-fine geometric character representation for efficient synthesis, which can be solely supervised on multi-view imagery.

[pdf]



Deep Physics-aware Inference of Cloth Deformation for Monocular Human Performance Capture

Yue Li   Marc Habermann   Bernhard Thomaszewski   Stelian Coros   Thabo Beeler   Christian Theobalt

3DV 2021

Abstract
Recent monocular human performance capture approaches have shown compelling dense tracking results of the full body from a single RGB camera. However, existing methods either do not estimate clothing at all or model cloth deformation with simple geometric priors instead of taking into account the underlying physical principles. This leads to noticeable artifacts in their reconstructions, such as baked-in wrinkles, implausible deformations that seemingly defy gravity, and intersections between cloth and body. To address these problems, we propose a person-specific, learning-based method that integrates a finite element-based simulation layer into the training process to provide for the first time physics supervision in the context of weakly-supervised deep monocular human performance capture. We show how integrating physics into the training process improves the learned cloth deformations, allows modeling clothing as a separate piece of geometry, and largely reduces cloth-body intersections. Relying only on weak 2D multi-view supervision during training, our approach leads to a significant improvement over current state-of-the-art methods and is thus a clear step towards realistic monocular capture of the entire deforming surface of a clothed human.

[pdf], [video], [project page], [arxiv]



Efficient and Differentiable Shadow Computation for Inverse Problems

Linjie Lyu   Marc Habermann   Lingjie Liu   Mallikarjun B R   Ayush Tewari  
Christian Theobalt  

ICCV 2021

Abstract
Differentiable rendering has received increasing interest for image-based inverse problems. It can benefit traditional optimization-based solutions to inverse problems, but also allows for self-supervision of learning-based approaches for which training data with ground truth annotation is hard to obtain. However, existing differentiable renderers either do not model visibility of the light sources from the different points in the scene, responsible for shadows in the images, or are too slow for being used to train deep architectures over thousands of iterations. To this end, we propose an accurate yet efficient approach for differentiable visibility and soft shadow computation. Our approach is based on the spherical harmonics approximations of the scene illumination and visibility, where the occluding surface is approximated with spheres. This allows for a significantly more efficient shadow computation compared to methods based on ray tracing. As our formulation is differentiable, it can be used to solve inverse problems such as texture, illumination, rigid pose, and geometric deformation recovery from images using analysis-by-synthesis optimization.

[pdf], [video], [project page], [arxiv]



A Deeper Look into DeepCap

Marc Habermann   Weipeng Xu   Michael Zollhoefer   Gerard Pons-Moll   Christian Theobalt

TPAMI 2021 Invited Paper

Abstract
Human performance capture is a highly important computer vision problem with many applications in movie production and virtual/augmented reality. Many previous performance capture approaches either required expensive multi-view setups or did not recover dense space-time coherent geometry with frame-to-frame correspondences. We propose a novel deep learning approach for monocular dense human performance capture. Our method is trained in a weakly supervised manner based on multi-view supervision completely removing the need for training data with 3D ground truth annotations. The network architecture is based on two separate networks that disentangle the task into a pose estimation and a non-rigid surface deformation step. Extensive qualitative and quantitative evaluations show that our approach outperforms the state of the art in terms of quality and robustness. This work is an extended version of DeepCap where we provide more detailed explanations, comparisons and results as well as applications.

[pdf], [project page], [arxiv], [dataset]



Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control

Lingjie Liu   Marc Habermann   Viktor Rudnev   Kripasindhu Sarkar   Jiatao Gu  
Christian Theobalt

SIGGRAPH Asia 2021

Abstract
We propose Neural Actor (NA), a new method for high-quality synthesis of humans from arbitrary viewpoints and under arbitrary controllable poses. Our method is built upon recent neural scene representation and rendering works which learn representations of geometry and appearance from only 2D images. While existing works demonstrated compelling rendering of static scenes and playback of dynamic scenes, photo-realistic reconstruction and rendering of humans with neural implicit methods, in particular under user-controlled novel poses, is still difficult. To address this problem, we utilize a coarse body model as the proxy to unwarp the surrounding 3D space into a canonical pose. A neural radiance field learns pose-dependent geometric deformations and pose- and view-dependent appearance effects in the canonical space from multi-view video input. To synthesize novel views of high fidelity dynamic geometry and appearance, we leverage 2D texture maps defined on the body model as latent variables for predicting residual deformations and the dynamic appearance. Experiments demonstrate that our method achieves better quality than the state-of-the-arts on playback as well as novel pose synthesis, and can even generalize well to new poses that starkly differ from the training poses. Furthermore, our method also supports body shape control of the synthesized results.

[pdf], [project page], [arxiv]



Real-time Deep Dynamic Characters

Marc Habermann   Lingjie Liu   Weipeng Xu   Michael Zollhoefer   Gerard Pons-Moll   Christian Theobalt

SIGGRAPH 2021

Abstract
We propose a deep videorealistic 3D human character model displaying highly realistic shape, motion, and dynamic appearance learned in a new weakly supervised way from multi-view imagery. In contrast to previous work, our controllable 3D character displays dynamics, e.g., the swing of the skirt, dependent on skeletal body motion in an efficient data-driven way, without requiring complex physics simulation. Our character model also features a learned dynamic texture model that accounts for photo-realistic motion-dependent appearance details, as well as view-dependent lighting effects. During training, we do not need to resort to difficult dynamic 3D capture of the human; instead we can train our model entirely from multi-view video in a weakly supervised manner. To this end, we propose a parametric and differentiable character representation which allows us to model coarse and fine dynamic deformations, e.g., garment wrinkles, as explicit space-time coherent mesh geometry that is augmented with high-quality dynamic textures dependent on motion and view point. As input to the model, only an arbitrary 3D skeleton motion is required, making it directly compatible with the established 3D animation pipeline. We use a novel graph convolutional network architecture to enable motion-dependent deformation learning of body and clothing, including dynamics, and a neural generative dynamic texture model creates corresponding dynamic texture maps. We show that by merely providing new skeletal motions, our model creates motion-dependent surface deformations, physically plausible dynamic clothing deformations, as well as video-realistic surface textures at a much higher level of detail than previous state of the art approaches, and even in real-time.

[pdf], [video], [project page], [arxiv], [dataset]



Monocular Real-time Full Body Capture with Inter-part Correlations

Yuxiao Zhou   Marc Habermann   Ikhsanul Habibie   Ayush Tewari   Christian Theobalt  
Feng Xu  

CVPR 2021

Abstract
We present the first method for real-time full body capture that estimates shape and motion of body and hands together with a dynamic 3D face model from a single color image. Our approach uses a new neural network architecture that exploits correlations between body and hands at high computational efficiency. Unlike previous works, our approach is jointly trained on multiple datasets focusing on hand, body or face separately, without requiring data where all the parts are annotated at the same time, which is much more difficult to create at sufficient variety. The possibility of such multi-dataset training enables superior generalization ability. In contrast to earlier monocular full body methods, our approach captures more expressive 3D face geometry and color by estimating the shape, expression, albedo and illumination parameters of a statistical face model. Our method achieves competitive accuracy on public benchmarks, while being significantly faster and providing more complete face reconstructions.

[pdf], [video], [project page], [arxiv]


2020



Differentiable Rendering Tool

Marc Habermann   Mallikarjun B R   Ayush Tewari   Linjie Lyu   Christian Theobalt

Github

Abstract This is a simple and efficient differentiable rasterization-based renderer which has been used in several GVV publications. The implementation is free of most third-party libraries such as OpenGL. The core implementation is in CUDA and C++. We use the layer as a custom Tensorflow op. The renderer supports the following features:
  • Shading based on spherical harmonics illumination. This shading model is differentiable with respect to geometry, texture, and lighting.
  • Different visualizations, such as normals, UV coordinates, phong-shaded surface, spherical-harmonics shading and colors without shading.
  • Texture map lookups.
  • Rendering from multiple camera views in a single batch

[Github]



DeepCap: Monocular Human Performance Capture Using Weak Supervision

Marc Habermann   Weipeng Xu   Michael Zollhoefer   Gerard Pons-Moll   Christian Theobalt

CVPR 2020 (Oral) CVPR 2020 Best Student Paper Honorable Mention

Abstract
Human performance capture is a highly important computer vision problem with many applications in movie production and virtual/augmented reality. Many previous performance capture approaches either required expensive multi-view setups or did not recover dense space-time coherent geometry with frame-to-frame correspondences. We propose a novel deep learning approach for monocular dense human performance capture. Our method is trained in a weakly supervised manner based on multi-view supervision completely removing the need for training data with 3D ground truth annotations. The network architecture is based on two separate networks that disentangle the task into a pose estimation and a non-rigid surface deformation step. Extensive qualitative and quantitative evaluations show that our approach outperforms the state of the art in terms of quality and robustness.

[pdf], [video], [project page], [arxiv], [dataset]



Neural Human Video Rendering by Learning Dynamic Textures and Rendering-to-Video Translation

Lingjie Liu   Weipeng Xu   Marc Habermann   Michael Zollhoefer   Florian Bernard   Hyeongwoo Kim   Wenping Wang   Christian Theobalt

TVCG 2020

Abstract
Synthesizing realistic videos of humans using neural networks has been a popular alternative to the conventional graphics-based rendering pipeline due to its high efficiency. Existing works typically formulate this as an image-to-image translation problem in 2D screen space, which leads to artifacts such as over-smoothing, missing body parts, and temporal instability of fine-scale detail, such as pose-dependent wrinkles in the clothing. In this paper, we propose a novel human video synthesis method that approaches these limiting factors by explicitly disentangling the learning of time-coherent fine-scale details from the embedding of the human in 2D screen space. More specifically, our method relies on the combination of two convolutional neural networks (CNNs). Given the pose information, the first CNN predicts a dynamic texture map that contains time-coherent high-frequency details, and the second CNN conditions the generation of the final video on the temporally coherent output of the first CNN. We demonstrate several applications of our approach, such as human reenactment and novel view synthesis from monocular video, where we show significant improvement over the state of the art both qualitatively and quantitatively.



[pdf], [video], [project page], [arxiv]



EventCap: Monocular 3D Capture of High-Speed Human Motions using an Event Camera

Lan Xu   Weipeng Xu   Vladislav Golyanik   Marc Habermann   Lu Fang   Christian Theobalt

CVPR 2020 (Oral)

Abstract
The high frame rate is a critical requirement for capturing fast human motions. In this setting, existing markerless image-based methods are constrained by the lighting requirement, the high data bandwidth and the consequent high computation overhead. In this paper, we propose EventCap — the first approach for 3D capturing of high-speed human motions using a single event camera. Our method combines model-based optimization and CNN-based human pose detection to capture high-frequency motion details and to reduce the drifting in the tracking. As a result, we can capture fast motions at millisecond resolution with significantly higher data efficiency than using highframe rate videos. Experiments on our new event-based fast human motion dataset demonstrate the effectiveness and accuracy of our method, as well as its robustness to challenging lighting conditions.

[pdf], [video], [project page], [arxiv]



Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data

Yuxiao Zhou   Marc Habermann   Weipeng Xu   Ikhsanul Habibie   Christian Theobalt  
Feng Xu

CVPR 2020

Abstract
We present a novel method for monocular hand shape and pose estimation at unprecedented runtime performance of 100fps and at state-of-the-art accuracy. This is enabled by a new learning based architecture designed such that it can make use of all the sources of available hand training data: image data with either 2D or 3D annotations, as well as stand-alone 3D animations without corresponding image data. It features a 3D hand joint detection module and an inverse kinematics module which regresses not only 3D joint positions but also maps them to joint rotations in a single feed-forward pass. This output makes the method more directly usable for applications in computer vision and graphics compared to only regressing 3D joint positions. We demonstrate that our architectural design leads to a significant quantitative and qualitative improvement over the state of the art on several challenging benchmarks. We will make our code publicly available for future research.

[pdf], [video], [project page], [arxiv]


2019



LiveCap: Real-time Human Performance Capture from Monocular Video

Marc Habermann   Weipeng Xu   Michael Zollhoefer   Gerard Pons-Moll   Christian Theobalt

ACM ToG 2019 @ SIGGRAPH 2019

Abstract
We present the first real-time human performance capture approach that reconstructs dense, space-time coherent deforming geometry of entire humans in general everyday clothing from just a single RGB video.We propose a novel two-stage analysis-by-synthesis optimization whose formulation and implementation are designed for high performance. In the first stage, a skinned template model is jointly fitted to background subtracted input video, 2D and 3D skeleton joint positions found using a deep neural network, and a set of sparse facial landmark detections. In the second stage, dense non-rigid 3D deformations of skin and even loose apparel are captured based on a novel real-time capable algorithm for non-rigid tracking using dense photometric and silhouette constraints. Our novel energy formulation leverages automatically identified material regions on the template to model the differing non-rigid deformation behavior of skin and apparel. The two resulting nonlinear optimization problems per-frame are solved with specially-tailored data-parallel Gauss-Newton solvers. In order to achieve real-time performance of over 25Hz, we design a pipelined parallel architecture using the CPU and two commodity GPUs. Our method is the first real-time monocular approach for full-body performance capture. Our method yields comparable accuracy with off-line performance capture techniques, while being orders of magnitude faster.

[pdf], [video], [project page], [arxiv]



Neural Animation and Reenactment of Human Actor Videos

Lingjie Liu   Weipeng Xu   Michael Zollhoefer   Hyeongwoo Kim   Florian Bernard  
Marc Habermann   Wenping Wang   Christian Theobalt

ACM ToG 2019 @ SIGGRAPH 2019

Abstract
We propose a method for generating (near) video-realistic animations of real humans under user control. In contrast to conventional human character rendering, we do not require the availability of a production-quality photo-realistic 3D model of the human, but instead rely on a video sequence in conjunction with a (medium-quality) controllable 3D template model of the person. With that, our approach significantly reduces production cost compared to conventional rendering approaches based on production-quality 3D models, and can also be used to realistically edit existing videos. Technically, this is achieved by training a neural network that translates simple synthetic images of a human character into realistic imagery. For training our networks, we first track the 3D motion of the person in the video using the template model, and subsequently generate a synthetically rendered version of the video. These images are then used to train a conditional generative adversarial network that translates synthetic images of the 3D model into realistic imagery of the human. We evaluate our method for the reenactment of another person that is tracked in order to obtain the motion data, and show video results generated from artist-designed skeleton motion. Our results outperform the state-of-the-art in learning-based human image synthesis.

[pdf], [video], [project page], [arxiv]


2018



NRST: Non-rigid Surface Tracking from Monocular Video

Marc Habermann   Weipeng Xu   Helge Rhodin   Michael Zollhoefer   Gerard Pons-Moll   Christian Theobalt

Oral @ German Conference on Pattern Recognition (GCPR) 2018

Abstract
We propose an efficient method for non-rigid surface tracking from monocular RGB videos. Given a video and a template mesh, our algorithm sequentially registers the template non-rigidly to each frame.We formulate the per-frame registration as an optimization problem that includes a novel texture term specifically tailored towards tracking objects with uniform texture but fine-scale structure, such as the regular micro-structural patterns of fabric. Our texture term exploits the orientation information in the micro-structures of the objects, e.g., the yarn patterns of fabrics. This enables us to accurately track uniformly colored materials that have these high frequency micro-structures, for which traditional photometric terms are usually less effective. The results demonstrate the effectiveness of our method on both general textured non-rigid objects and monochromatic fabrics.

[pdf], [video], [project page], [arxiv]



Awards & Honors

Education & Recent Positions

  • November 2021 - now
    Research group leader at the Max Planck Institute for Informatics in the Visual Computing and Artificial Intelligence Department, Saarbrücken, Germany

  • November 2021 - now
    Head of the Real Virtual Lab at the Max Planck Institute for Informatics in the Visual Computing and Artificial Intelligence Department, Saarbrücken, Germany

  • October 2021
    Dr.-Ing. (PhD) degree in Computer Science, Max Planck Institute for Informatics / Saarland University, Saarbrücken, Germany

  • September 2017 - October 2021
    PhD student at the Max Planck Institute for Informatics in the Visual Computing and Artificial Intelligence Department, Saarbrücken, Germany

  • April 2016 - November 2017
    Master Studies in Computer Science at Saarland University, Saarbrücken, Germany
    Title of Master's Thesis (Diplomarbeit): RONDA - Reconstruction of Non-rigid Surfaces from High Resolution Video (supervisor: Prof. Dr. Christian Theobalt) (PDF)

  • October 2012 - April 2016:
    Bachelor Studies in Computer Science at Saarland University, Saarbrücken, Germany
    Title of Bachelor's Thesis: Drone Path Planning (supervisor: Dr.-Ing. Tobias Ritschel) (PDF)

  • July 2012:
    Abitur at the Albertus Magnus Gymnasium, Sankt Ingbert, Germany

Teaching

  • October 2023 - February 2024
    Lecturer for Advanced Topics in Neural Rendering and Reconstruction, Lecturer: Prof. Dr. Christian Theobalt, Dr. Mohamed Elgharib, Dr. Vladislav Golyanik, Dr. Thomas Leimkühler, Dr. Marc Habermann at the Saarland University, Saarbrücken, Germany

  • April 2022 - August 2022
    Lecturer for Computer Vision and Machine Learning for Computer Graphics, Lecturer: Prof. Dr. Christian Theobalt, Dr. Marc Habermann, Dr. Thomas Leimkühler at the Saarland University, Saarbrücken, Germany

  • April 2021 - August 2021
    Supervisor for Computer Vision and Machine Learning for Computer Graphics, Lecturer: Prof. Dr. Christian Theobalt, Dr. Mohamed Elgharib, Dr. Vladislav Golyanik at the Saarland University, Saarbrücken, Germany

  • April 2020 - August 2020
    Supervisor for Computer Vision and Machine Learning for Computer Graphics, Lecturer: Prof. Dr. Christian Theobalt, Dr. Mohamed Elgharib, Dr. Vladislav Golyanik at the Saarland University, Saarbrücken, Germany

  • April 2019 - August 2019
    Supervisor for Computer Vision and Machine Learning for Computer Graphics, Lecturer: Prof. Dr. Christian Theobalt, Dr. Mohamed Elgharib, Dr. Vladislav Golyanik at the Saarland University, Saarbrücken, Germany

  • April 2018 - August 2018
    Supervisor for 3D Shape Analysis, Lecturer: Dr. Florian Bernard and Prof. Dr. Christian Theobalt at the Saarland University, Saarbrücken, Germany

  • September 2016 - June 2018
    Tutor for Seminarfach 3D Modellierung at the Leibniz Gymnasium/Albertus Magnus Gymnasium, Sankt Ingbert, Germany

  • July 2013 - September 2016:
    Tutor for 3D Modellierung Alte Schmelz, Sankt Ingbert, Germany

Reviewing

I also regularly serve as reviewer for the following conferences and journals:

  • SIGGRAPH
  • SIGGRAPH Asia
  • CVPR
  • ECCV
  • CRV
  • ToG
  • TPAMI
  • IJCV
  • TVCG
  • TCSVT
  • CVIU
  • PG
  • 3DV

Private

Hobbies

  • Photography
  • Bouldering
  • Reading Books