Michael Oechsle

PhD Candidate at the MPI for Intelligent Systems, Uni Tuebingen and ETAS GmbH

I am a PhD student at the Max Planck Institute for Intelligent Systems supervised by Prof. Andreas Geiger and I am also part of the machine learning team of the ETAS GmbH.

My research focuses on novel 3D representations that enable deep learning techniques for various 3D Computer Vision tasks. I am particularly interested in 3D reconstruction of shape and appearance and novel view synthesis.

Prior to joining MPI and ETAS, I studied Physics (Bsc&Msc) at the University of Stuttgart, focussing on theoretical statistical Physics.

news

Jul 21, 2021 UNISURF got accepted as an oral presentation to ICCV2021
Aug 15, 2019 Texture Fields accepted as an oral presentation to ICCV2019

publications

  1. UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction
    Oechsle, Michael, Peng, Songyou, and Geiger, Andreas
    In International Conference on Computer Vision (ICCV) 2021
  2. Learning Implicit Surface Light Fields
    Oechsle, Michael, Niemeyer, Michael, Reiser, Christian, Mescheder, Lars, Strauss, Thilo, and Geiger, Andreas
    In International Conference on 3D Vision (3DV) 2020
  3. Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision
    In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2020
  4. Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics
    In International Conference on Computer Vision (ICCV) 2019
  5. Texture Fields: Learning Texture Representations in Function Space
    Oechsle, Michael, Mescheder, Lars, Niemeyer, Michael, Strauss, Thilo, and Geiger, Andreas
    In International Conference on Computer Vision (ICCV) 2019
  6. Occupancy Networks: Learning 3D Reconstruction in Function Space
    Mescheder, Lars, Oechsle, Michael, Niemeyer, Michael, Nowozin, Sebastian, and Geiger, Andreas
    In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2019