English

Volume Rendering Digest (for NeRF)

Computer Vision and Pattern Recognition 2022-09-07 v1 Graphics

Abstract

Neural Radiance Fields employ simple volume rendering as a way to overcome the challenges of differentiating through ray-triangle intersections by leveraging a probabilistic notion of visibility. This is achieved by assuming the scene is composed by a cloud of light-emitting particles whose density changes in space. This technical report summarizes the derivations for differentiable volume rendering. It is a condensed version of previous reports, but rewritten in the context of NeRF, and adopting its commonly used notation.

Keywords

Cite

@article{arxiv.2209.02417,
  title  = {Volume Rendering Digest (for NeRF)},
  author = {Andrea Tagliasacchi and Ben Mildenhall},
  journal= {arXiv preprint arXiv:2209.02417},
  year   = {2022}
}

Comments

Overleaf: https://www.overleaf.com/read/fkhpkzxhnyws

R2 v1 2026-06-28T00:47:43.858Z