Geometry-Guided Ray Augmentation for Neural Surface Reconstruction with Sparse Views

arXiv:2310.05483v4 Announce Type: replace
Abstract: In this paper, we propose a novel method for 3D scene and object reconstruction from sparse multi-view images. Different from previous methods that leverage extra information such as depth or generalizable features across scenes, our approach leverages the scene properties embedded in the multi-view inputs to create precise pseudo-labels for optimization without any prior training. Specifically, we introduce a geometry-guided approach that improves surface reconstruction accuracy from sparse views by leveraging spherical harmonics to predict …

abstract arxiv augmentation cs.cv embedded extra features geometry images information inputs novel object paper ray surface type view