MPI-INF Logo
Homepage

Contact

Firstname Lastname

Mallikarjun B R

(M. Byrasandra Ramalinga Reddy)
Max-Planck-Institut für Informatik
D6: Visual Computing and Artificial Intelligence
 office: Campus E1 4, Room 211B
Saarland Informatics Campus
66123 Saarbrücken
Germany
 email: mbr@mpi-inf.mpg.de
 phone: +49 681 9325 4056
 fax: +49 681 9325 4099

Research Interests

  • Computer Vision
  • Computer Graphics

Publications

LiveHand: Real-time and Photorealistic Neural Hand Rendering
Akshay Mundra, Mallikarjun B R, Jiayi Wang, Marc Habermann, Christian Theobalt and Mohamad Elgharib

International Conference on Computer Vision 2023 (ICCV)   —   ICCV 2023


[paper] [project page]


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

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 from 2D image observations. We then start from general methods, and proceed towards techniques making stronger assumptions about the observed objects (e.g. human faces, bodies, hands, and animals). We conclude by discussing open challenges in the field and the social aspects associated with the usage of the reviewed methods.

Eurographics 2023 (STAR Report)    

[Project Page] [arXiv]



VoRF: Volumetric Relightable Faces
P. Rao, M. B R, G. Fox, T. Weyrich, B. Bickel, H. Pfister, W. Matusik, A. Tewari, C. Theobalt and M. Elgharib

British Machine Vision Conference 2022 (BMVC)   —   BMVC 2022 (Best Paper Award Honourable Mention)

We present a volumetric relightable head model, which can igeneralize to unseen identities, even with a single input image.
[paper] [project page]


gCoRF: Generative Compositional Radiance Fields
M. B R, A. Tewari, X. Pan, M. Elgharib and C. Theobalt

International Conference on 3D Vision (3DV)   —   3DV 2022 (Spotlight)

We present a compositional generative model, where each semantic part of the object is represented as an independent 3D representation learnt from only in-the-wild 2D data.
[paper] [project page]


Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images
A. Tewari, M. B R, X. Pan, O. Fried and M. Agarwala and C. Theobalt

Proc. Computer Vision and Pattern Recognition 2022   —   CVPR 2022

We design a 3D GAN which can learn a disentangled model of objects, just from monocular observations. Our model can disentangle the geometry and appearance variations in the scene, i.e., we can independently sample from the geometry and appearance spaces of the generative model.
[paper] [project page]


PhotoApp: Photorealistic Appearance Editing of Head Portraits
M. B R, A. Tewari, A. Dib, T. Weyrich, B. Bickel, H-P. Seidel, H. Pfister, W. Matusik, L. Chevalier, M. Elgharib and C. Theobalt

ACM Transactions on Graphics (Proc. of SIGGRAPH 2021)   —   SIGGRAPH 2021

We present a method for high-quality appearance editing of head portraits. A supervised learning problem is designed in the latent space of the StyleGAN network. This allows for generalization to in-the-wild images, even when trained on a small light-stage dataset.
[paper] [project page]


Efficient and Differentiable Shadow Computation for Inverse Problems
L. Lyu, M. Habermann, L. Liu, M. B R, A. Tewari and C. Theobalt

Proc. International Conference on Computer Vision 2021   —   ICCV 2021

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.
[paper] [project page]


Monocular Reconstruction of Neural Face Reflectance Fields
M. B R, A. Tewari, T-H. Oh, T. Weyrich, B. Bickel, H-P. Seidel, H. Pfister, W. Matusik, M. Elgharib and C. Theobalt

Proc. Computer Vision and Pattern Recognition 2021   —   CVPR 2021

We present a new neural representation for face reflectance where we can estimate all components of the reflectance responsible for the final appearance from a single monocular image.
[paper] [project page]


Learning Complete 3D Morphable Face Models from Images and Videos
M. B R, A. Tewari, H-P. Seidel, M. Elgharib and C. Theobalt

Proc. Computer Vision and Pattern Recognition 2021   —   CVPR 2021

We present the first approach to learn complete 3D models of face identity geometry, albedo and expression just from images and videos.
[paper] [project page]


PIE: Portrait Image Embedding for Semantic Control
A. Tewari, M. Elgharib, M. B R, F. Bernard, H-P. Seidel, P. Perez, M. Zollhöfer and C. Theobalt

ACM Transactions on Graphics (Proc. of SIGGRAPH Asia 2020)   —   SIGGRAPH Asia 2020

We present the first approach for embedding real portrait images in the latent space of StyleGAN which allows for intuitive editing of the head pose, facial expression, and scene illumination in the image.
[paper] [video] [Talk] [project page]


Education