Occupancy Networks: Learning 3D Reconstruction in Function Space

CVPR 2019 Lars MeschederMichael OechsleMichael NiemeyerSebastian NowozinAndreas Geiger

With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity. However, unlike for images, in 3D there is no canonical representation which is both computationally and memory efficient yet allows for representing high-resolution geometry of arbitrary topology... (read more)

PDF Abstract

Evaluation results from the paper

  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.