Re-Nerfing: Improving Novel Views Synthesis through Novel Views Synthesis

arXiv:2312.02255v2 Announce Type: replace
Abstract: Neural Radiance Fields (NeRFs) have shown remarkable novel view synthesis capabilities even in large-scale, unbounded scenes, albeit requiring hundreds of views or introducing artifacts in sparser settings. Their optimization suffers from shape-radiance ambiguities wherever only a small visual overlap is available. This leads to erroneous scene geometry and artifacts. In this paper, we propose Re-Nerfing, a simple and general multi-stage data augmentation approach that leverages NeRF's own view synthesis ability to address these limitations. With …

arxiv cs.cv cs.gr cs.lg improving novel synthesis through type