Anisotropic Neural Representation Learning for High-Quality Neural Rendering

arXiv:2311.18311v2 Announce Type: replace
Abstract: Neural radiance fields (NeRFs) have achieved impressive view synthesis results by learning an implicit volumetric representation from multi-view images. To project the implicit representation into an image, NeRF employs volume rendering that approximates the continuous integrals of rays as an accumulation of the colors and densities of the sampled points. Although this approximation enables efficient rendering, it ignores the direction information in point intervals, resulting in ambiguous features and limited reconstruction quality. In this paper, …

abstract arxiv colors continuous cs.cv cs.gr fields image images nerf neural radiance fields neural rendering project quality rendering representation representation learning results synthesis type view