NeRF++: Analyzing and Improving Neural Radiance Fields

Kai Zhang; Gernot Riegler; Noah Snavely; Vladlen Koltun

NeRF++: Analyzing and Improving Neural Radiance Fields

Computer Vision and Pattern Recognition 2020-10-23 v2

Authors: Kai Zhang , Gernot Riegler , Noah Snavely , Vladlen Koltun

Abstract

Neural Radiance Fields (NeRF) achieve impressive view synthesis results for a variety of capture settings, including 360 capture of bounded scenes and forward-facing capture of bounded and unbounded scenes. NeRF fits multi-layer perceptrons (MLPs) representing view-invariant opacity and view-dependent color volumes to a set of training images, and samples novel views based on volume rendering techniques. In this technical report, we first remark on radiance fields and their potential ambiguities, namely the shape-radiance ambiguity, and analyze NeRF's success in avoiding such ambiguities. Second, we address a parametrization issue involved in applying NeRF to 360 captures of objects within large-scale, unbounded 3D scenes. Our method improves view synthesis fidelity in this challenging scenario. Code is available at https://github.com/Kai-46/nerfplusplus.

Keywords

neural radiance field rendering novel view synthesis

Cite

@article{arxiv.2010.07492,
  title  = {NeRF++: Analyzing and Improving Neural Radiance Fields},
  author = {Kai Zhang and Gernot Riegler and Noah Snavely and Vladlen Koltun},
  journal= {arXiv preprint arXiv:2010.07492},
  year   = {2020}
}

Comments

Code is available at https://github.com/Kai-46/nerfplusplus; fix a minor formatting issue in Fig. 4

NeRF++: Analyzing and Improving Neural Radiance Fields

Abstract

Keywords

Cite

Comments

Related papers