Monocular Differentiable Rendering for Self-Supervised 3D Object Detection

Authors:
  • DBDeniz Beker
    Deniz Beker
  • HKHiroharu Kato
    Hiroharu Kato
  • MMMihai Adrian Morariu
    Mihai Adrian Morariu
  • TATakahiro Ando
    Takahiro Ando
  • TMToru Matsuoka
    Toru Matsuoka
  • WKWadim Kehl
    Wadim Kehl
  • AGAdrien Gaidon
    Adrien Gaidon

Abstract
3D object detection from monocular images is an ill-posed problem due to the projective entanglement of depth and scale. To overcome this ambiguity, we present a novel self-supervised method for textured 3D shape reconstruction and pose estimation of rigid objects with the help of strong shape priors and 2D instance masks. Our method predicts the 3D location and meshes of each object in an image using differentiable rendering and a self-supervised objective derived from a pretrained monocular depth estimation network. We use the KITTI 3D object detection dataset to evaluate the accuracy of the method. Experiments demonstrate that we can effectively use noisy monocular depth and differentiable rendering as an alternative to expensive 3D ground-truth labels or LiDAR information.
All Related Versions