Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency

arXiv:2403.17638v1 Announce Type: new
Abstract: We propose a voxel-based optimization framework, ReVoRF, for few-shot radiance fields that strategically address the unreliability in pseudo novel view synthesis. Our method pivots on the insight that relative depth relationships within neighboring regions are more reliable than the absolute color values in disoccluded areas. Consequently, we devise a bilateral geometric consistency loss that carefully navigates the trade-off between color fidelity and geometric accuracy in the context of depth consistency for uncertain regions. Moreover, we …

arxiv cs.cv few-shot fields type voxel