MPI-INF Logo
Homepage

Contact

Firstname Lastname

Soshi Shimada

Max-Planck-Institut für Informatik
D6: Visual Computing and Artificial Intelligence
 office: Campus E1 4,
Saarland Informatics Campus
66123 Saarbrücken
Germany
 email: sshimada [at] mpi-inf dot mpg dot de

Experiences

Research Summary

  • Topic: Physically plausible monocular 3D human motion capture and synthesis with interactions.
  • Approach: My works include reconstructing 3D human motions from an RGB sequence explicitly integrating 1) physics equations and/or 2) modelling of interactions with the environment in the motion capture pipeline for improved realism. Furthermore, my recent work extends beyond capturing human motions alone and includes surface deformations resulting from self-interactions (e.g., punching a face) from an RGB video. Additionally, one of my projects involves the diffusion model based synthesis of hand-object interactions.
  • Publications: CVPR, ECCV, ICCV, SIGGRAPH, SIGGRAPH Asia, TPAMI, etc.

Research Interests

  • Physics based 3D Human motion capture
  • Motion capture with interactions
  • Rigid body dynamics
  • Non-Rigid surface deformation capture
  • Machine learning

Publications

2024

    MACS: Mass Conditioned 3D Hand and Object Motion Synthesis
    S. Shimada, F. Mueller, J. Bednařík, B. Doosti, B. Bickel, D. Tang, V. Golyanik, J. Taylor, C. Theobalt and T. Beeler.
    Accepted at International Conference on 3D Vision (3DV), 2024

    [project page] [paper]
2023

    Decaf: Monocular Deformation Capture for Face and Hand Interactions
    S. Shimada, V. Golyanik, P. Pérez and C. Theobalt.
    ACM Transactions on Graphic (SIGGRAPH Asia), 2023.

    [project page] [paper] [dataset]
    Unbiased 4D: Monocular 4D Reconstruction with a Neural Deformation Model
    E. Johnson, M. Habermann, S. Shimada, V. Golyanik and C. Theobalt
    Accepted at Computer Vision and Pattern Recognition Workshop (CVPRW), 2023.



    [project page] [paper]
2022

    MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenes
    Z. Li, S. Shimada, B. Schiele, C. Theobalt and V. Golyanik
    Accepted at 3D Vision (3DV), 2022.
    (Best Student Paper Award)


    [project page] [paper]
    HULC: 3D Human Motion Capture with Pose Manifold Sampling and Dense Contact Guidance
    S. Shimada, V. Golyanik, Z Li, P. Pérez, W. Xu, and C. Theobalt
    Accepted at European Conference on Computer Vision (ECCV), 2022.


    [project page] [paper]
    UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture
    H. Akada, J. Wang ,S. Shimada, M. Takahashi, C. Theobalt and V. Golyanik
    Accepted at European Conference on Computer Vision (ECCV), 2022.


    [project page]
    Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensors
    X. Yi, Y. Zhou, M. Habermann, S. Shimada, V. Golyanik, C. Theobalt, and F. Xu
    Accepted at Computer Vision and Pattern Recognition (CVPR), 2022. (Best Paper Finalist)


    [paper] [project page]
2021

    HandVoxNet++: 3D Hand Shape and Pose Estimation using Voxel-Based Neural Networks
    J. Malik S. Shimada, A. Elhayek, S. Ali, C. Theobalt, V. Golyanik and D. Stricker,
    Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021.

    [paper] [project page]
    Gravity-Aware 3D Human-Object Reconstruction
    R. Dabral, S. Shimada, A. Jain, C. Theobalt and V. Golyanik,
    In International Conference on Computer Vision (ICCV), 2021.

    [paper] [project page] [code] [dataset]
    Neural Monocular 3D Human Motion Capture with Physical Awareness
    S. Shimada, V. Golyanik, W. Xu, P. Pérez and C. Theobalt.
    ACM Transactions on Graphic (SIGGRAPH), 2021.

    [paper] [project page]
2020

    PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time
    S. Shimada, V. Golyanik, W. Xu and C. Theobalt.
    ACM Transactions on Graphic (SIGGRAPH Asia), 2020.

    [paper] [project page] [arXiv]
    Fast Simultaneous Gravitational Alignment of Multiple Point Sets
    V. Golyanik, S. Shimada and C. Theobalt.
    In International Conference on 3D Vision (3DV), 2020 (Oral)

    [paper] [project page]
    HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation from a Single Depth Map
    J. Malik, I. Abdelaziz, A. Elhayek, S. Shimada, S. A. Ali, V. Golyanik, C. Theobalt and D. Stricker.
    Accepted in Computer Vision and Pattern Recognition (CVPR), 2020.
    [paper] [supplement] [project page] [arXiv]

2019
    DispVoxNets: Non-Rigid Point Set Alignment with Supervised Learning Proxies.
    S. Shimada, V. Golyanik, E. Tretschk, D. Stricker and C. Theobalt.
    In International Conference on 3D Vision (3DV), 2019; Oral
    [paper] [poster] [project page] [arXiv]

    IsMo-GAN: Adversarial Learning for Monocular Non-Rigid 3D Reconstruction.
    S. Shimada, V. Golyanik, C. Theobalt and D. Stricker.
    In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2019; Oral

    [paper] [code] [arXiv]
2018
    HDM-Net: Monocular Non-Rigid 3D Reconstruction with Learned Deformation Model.
    V. Golyanik, S. Shimada, K. Varanasi and D. Stricker.
    In International Conference on Virtual Reality and Augmented Reality (EuroVR) 2018; Oral (Long Paper)
    [paper] [HDM-Net data set]

Education