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

Jun 2026 Gave a talk on “Synthetic Worlds for Scalable Robot Learning” at the Synthetic Data for Robot Learning workshop at ICRA’26. Also co-organizing the Beyond Teleoperation workshop (June 5)!
Apr 2026 SceneSmith accepted to ICML’26 as a Spotlight (top 2.2%)!
Apr 2026 PolaRIS accepted to RSS’26!
Jan 2026 Humanoid Everyday accepted to ICRA’26!

selected publications

  1. RecGen: Reconstructive Generation of 3D Scenes from RGB-D Observations
    Andrii Zadaianchuk, Leonardo Barcellona, Lennard Schuenemann, and 7 more authors
    In arXiv, 2026
  2. SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes
    Nicholas Pfaff, Thomas Cohn, Sergey Zakharov, and 2 more authors
    In ICML, 2026
  3. 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
  4. Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors
    Sergey ZakharovWadim Kehl, Arjun Bhargava, and 1 more author
    In CVPR (Oral), 2020
  5. dpod.png
    DPOD: 6D Pose Object Detector and Refiner
    Sergey ZakharovIvan Shugurov, and Slobodan Ilic
    In ICCV, 2019
  6. hb.png
    HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects
    Roman KaskmanSergey ZakharovIvan Shugurov, and 1 more author
    In ICCVW, 2019