Sergey Zakharov

I am a machine learning research scientist at Toyota Research Institute and a former PhD candidate at the Chair for Computer Aided Medical Procedures, Technical University of Munich and Siemens AG. My research focuses on scene understanding and covers such topics as scalable 3D object detection, neural implicit representations, differentiable rendering, and domain adaptation.

Reviewer for CVPR, ICCV, BMVC, WACV, ICRA, IROS, RA-L, CVIU.

news

Sep 2021 Our paper on single shot scene reconstruction is accepted to CoRL!
Sep 2021 DPODv2 is accepted to TPAMI!
Oct 2020 Defended my PhD thesis! (Learning to Estimate 3D Object Pose from Synthetic Data)
Aug 2020 DPOD was awarded as the best method on the LM dataset at the BOP Challenge 2020 at ECCV’20.

selected publications

  1. SDFLabel
    Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors
    Zakharov, Sergey, Kehl, Wadim, Bhargava, Arjun, and Gaidon, Adrien
    In IEEE Computer Vision and Pattern Recognition (CVPR) 2020
  2. DPOD
    DPOD: 6D Pose Object Detector and Refiner
    Zakharov, Sergey, Shugurov, Ivan, and Ilic, Slobodan
    In IEEE International Conference on Computer Vision (ICCV) 2019
  3. DeceptionNet
    DeceptionNet: Network-Driven Domain Randomization
    Zakharov, Sergey, Kehl, Wadim, and Ilic, Slobodan
    In IEEE International Conference on Computer Vision (ICCV) 2019
  4. HomebrewedDB
    HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects
    Kaskman, Roman, Zakharov, Sergey, Shugurov, Ivan, and Ilic, Slobodan
    In IEEE International Conference on Computer Vision Workshops (ICCVW) 2019