CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs

arXiv:2403.16885v1 Announce Type: new
Abstract: Neural Radiance Fields (NeRF) have shown impressive capabilities for photorealistic novel view synthesis when trained on dense inputs. However, when trained on sparse inputs, NeRF typically encounters issues of incorrect density or color predictions, mainly due to insufficient coverage of the scene causing partial and sparse supervision, thus leading to significant performance degradation. While existing works mainly consider ray-level consistency to construct 2D learning regularization based on rendered color, depth, or semantics on image planes, …

abstract arxiv capabilities color consistent coverage cs.cv fields however inputs nerf neural radiance fields novel photorealistic predictions synthesis transformer type view voxel