Diogo C. Luvizon

Diogo Carbonera Luvizon

Max-Planck-Institut für Informatik
Department 6: Visual Computing and Artificial Intelligence
 office: Campus E1 4, Room 223
Saarland Informatics Campus
66123 Saarbrücken
 email: Get my email address via email
 phone: +49 681 9325 4540
 fax: +49 681 9325 4099


  • Jul. 2023: Patent granted by the USPTO! [ link ]
  • Mai.2023: SSP-Net accepted to Pattern Recognition.
  • Mar.2023: One paper accepted to CVPR 2023.
  • Feb.2023: One paper accepted to EUROGRAPHICS 2023.

Research Interests

  • Computer Vision & Computer Graphics
  • Human Pose Estimation and Action Recognition
  • 3D Scene Understanding


    SSP-Net: Scalable Sequential Pyramid Networks for Real-time 3D Human Pose Regression
    D. Luvizon, H. Tabia, D. Picard
    Pattern Recognition, Volume 142, Oct. 2023

    Description: In this paper, we propose a highly scalable convolutional neural network (SSP-Net) for real-time 3D human pose regression from a single image. The SSP-Net is trained with refined supervision at multiple scales in a sequential manner. Our network requires a single training procedure and is capable of producing its best predictions at 120 frames per second (FPS), or acceptable predictions at more than 200 FPS when cut at test time. We show that the proposed regression approach is invariant to the size of feature maps, allowing our method to perform multi-resolution intermediate supervisions.

    [paper] [arXiv]

    Scene-aware Egocentric 3D Human Pose Estimation
    J. Wang, D. Luvizon, W. Xu, L. Liu, K. Sarkar, and C. Theobalt
    To appear in CVPR 2023.

    Description: In this work, we propose to estimate egocentric human pose guided by scene constraints. We devise a new egocentric scene depth estimation network from a wide-view egocentric fisheye camera that estimates the depth behind the human with a depth-inpainting network. Our pose estimation model projects 2D image features and estimated scene depth into a common voxel space and regresses the 3D pose with a V2V network. We also generated a synthetic dataset, EgoGTA, and an in-the-wild dataset based on EgoPW, EgoPW-Scene.

    [paper] [IEEE/CVF] [arXiv] [project page] [code]

    Scene-Aware 3D Multi-Human Motion Capture from a Single Camera
    D. Luvizon, M. Habermann, V. Golyanik, A. Kortylewski and C. Theobalt
    Eurographics 2023.

    Description: 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. 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 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.

    [arXiv] [project page] [source code]

    HandFlow: Quantifying View-Dependent 3D Ambiguity in Two-Hand Reconstruction with Normalizing Flow
    J. Wang, D. Luvizon, F. Mueller, F. Bernard, A. Kortylewski, D. Casas, C. Theobalt
    VMV 2022, Best Paper Honorable Mention

    Description: This work presents the first probabilistic method to estimate a distribution of plausible two-hand poses given a monocular RGB input. It quantitatively shows that existing deterministic methods are not suited for this ambiguous task. In this work, we demonstrate the quality of our probabilistic reconstruction and show that explicit ambiguity modeling is better-suited for this challenging problem

    [arXiv] [project page]

    Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision
    J. Wang, L. Liu, W. Xu, K. Sarkar, D. Luvizon, C. Theobalt
    CVPR 2022

    Description: We present a new egocentric pose estimation method that can be trained with weak external supervision. To facilitate the network training, we propose a novel learning strategy to supervise the egocentric features with high-quality features extracted by a pretrained external-view pose estimation model. We also collected a large-scale in-the-wild egocentric dataset called Egocentric Poses in the Wild (EgoPW) with a head-mounted fisheye camera and an auxiliary external camera, which provides additional observation of the human body from a third-person perspective.

    [paper] [arXiv] [project page] [data]

    Adaptive multiplane image generation from a single internet picture
    Diogo C. Luvizon, Gustavo Sutter P Carvalho, Andreza A. dos Santos, Jhonatas S. Conceicao, Jose L. Flores-Campana, Luis G.L. Decker, Marcos R. Souza, Helio Pedrini, Antonio Joia, Otavio A.B. Penatti
    WACV 2021, CVPR 2021 Workshop Learning to Generate 3D Shapes and Scenes

    Description: In this paper, we address the problem of generating an efficient multiplane image (MPI) from a single high-resolution picture. We present the adaptive-MPI representation, which allows rendering novel views with low computational requirements. To this end, we propose an adaptive slicing algorithm that produces an MPI with variable number of image planes. We also present a new lightweight CNN for depth estimation, which is learned by knowledge distillation from a larger network. Occluded regions in the adaptive-MPI are inpainted also by a lightweight CNN.Our method is capable of producing high-quality predictions with one order of magnitude less parameters, when compared to previous approaches.

    [paper] [arXiv] [CVPRW'21 link]

Recent Positions

  • 2021 - current: Postdoctoral Researcher at MPI-INF VCAI
  • 2019 - 2021: Research Scientist at Samsung SRBR
  • 2011 - 2014: Electronic Engineer at Ensitec Tecnologia


  • 2015 - 2019: PhD Student at ETIS / Cergy-Paris Université (France), Individual Grant 233342/2014-1 CNPq
  • 2013 - 2015: MSc Degree in Applied Computing & Computer Vision, UTFPR/DAINF (Brazil)
  • 2007 - 2011: BSc Degree in Electronics Engineering, UTFPR (Brazil)
  • 2023: CVPR;  ICCV;  TPAMI;  C&G;  IEEE Signal Processing Letters;  SIBGRAPI;  Conference on Neural Information Processing Systems (NeurIPS);  SIGGRAPH Asia
  • 2022: CVPR;  TPAMI;  European Conference on Computer Vision (ECCV);  International Conference on 3D Vision (3DV);  IJCV;  Conference on Graphics, Patterns and Images (SIBGRAPI);  IEEE Trans. on Multimedia (TMM);  Elsevier Computer & Graphics (C&G)
  • 2021: CVPR;  International Conference on Computer Vision (ICCV);  Winter Conference on Applications of Computer Vision (WACV);  IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI);  IEEE Trans. on Intelligent Transportation Systems (ITS);  Elsevier Computer Vision and Image Understanding (CVIU)
  • 2020: Computer Vision and Pattern Recognition (CVPR);  Asian Conference on Computer Vision (ACCV);  International Journal of Computer Vision (IJCV);  Elsevier Pattern Recognition (PR)
  • 2018-2019: IEEE Trans. on Multimedia;  IEEE Signal Processing Letters
  • Best Paper Honorable Mention in the International Symposium on Vision, Modeling, and Visualization (VMV/GCPR), 2022, Konstanz, Germany.
  • Best presentation award in the annual ETIS Lab Workshop, 2018, France.
  • 1st Prize on Workshop of Thesis and Dissertations (WTD - Master), Conference on Graphics, Patterns and Images (SIBGRAPI), 2016, Brazil.
  • 2nd Prize on Concurso Latino-Americano de Dissertações de Mestrado (CLTM), Conferência Latino-Americana de Informática (CLEI), 2016, Chile.
  • Individual Grant from CNPq (233342/2014-1)
  • Teaching

    Master (ENSEA - France) 2017-2019

    UEC-1-IMD Int. images et multimedia

    • Action recognition from skeletons, VLAD, and LMNN: slides
    • Intro. to Neural Networks and Deep Learning: slides
    • Intro. to Generative Adversarial Networks: slides
    • IA et Big Data: TP GANs 2018-2019 link