Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields

arXiv:2404.17528v1 Announce Type: new
Abstract: Generalizable NeRF aims to synthesize novel views for unseen scenes. Common practices involve constructing variance-based cost volumes for geometry reconstruction and encoding 3D descriptors for decoding novel views. However, existing methods show limited generalization ability in challenging conditions due to inaccurate geometry, sub-optimal descriptors, and decoding strategies. We address these issues point by point. First, we find the variance-based cost volume exhibits failure patterns as the features of pixels corresponding to the same point can …

arxiv cs.cv fields fusion geometry neural radiance fields rendering type