Volume Rendering Digest (for NeRF)
This is an incremental technical summary for researchers working on NeRF and volume rendering methods.
The report summarizes derivations for differentiable volume rendering in the context of Neural Radiance Fields (NeRF), addressing the challenge of differentiating through ray-triangle intersections by using a probabilistic visibility model based on light-emitting particles with varying density.
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.