Sergey Zakharov

prof_pic.jpg

I am a Senior Research Scientist and Team Lead at Toyota Research Institute, specializing in 3D scene understanding to develop robust and versatile perception models that can infer rich representations of their environment from vision. My research spans generative modeling, implicit neural representations, 3D reconstruction, domain adaptation, and self-supervised learning, with a strong focus on generalization and real-world transfer. I earned my PhD from the Technical University of Munich, under the supervision of Slobodan Ilic.

news

Feb 2025 Our work on shape reconstruction enabled robotic grasping accepted to CVPR’25!
Jan 2025 Our work on multi-hypothesis shape and pose estimation accepted to ICRA’25!
Sep 2024 Our novel equivariant ray embedding representation is accepted to NeurIPS’24!
Sep 2024 VISTA is accepted to CoRL’24 in Munich!

selected publications

  1. 0123.png
    Zero-1-to-3: Zero-shot One Image to 3D Object
    Ruoshi LiuRundi WuBasile Van Hoorick, and 3 more authors
    In ICCV, 2023
  2. sdflabel.gif
    Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors
    Sergey ZakharovWadim Kehl, Arjun Bhargava, and 1 more author
    In CVPR (Oral), 2020
  3. dpod.png
    DPOD: 6D Pose Object Detector and Refiner
    Sergey ZakharovIvan Shugurov, and Slobodan Ilic
    In ICCV, 2019
  4. hb.png
    HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects
    Roman KaskmanSergey ZakharovIvan Shugurov, and 1 more author
    In ICCVW, 2019