NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections

2022년 03월 04일 (금) | 발표자: 정유호

NeRF-W learns a per-image latent embedding capturing photometric appearance variations often present in in-the-wild data, and decomposes the scene into image-dependent and shared components to allow the model to disentangle transient elements from the static scene.