UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and UnFavOrable Data Sets

arXiv:2403.05086v1 Announce Type: new
Abstract: Generalizable neural implicit surface reconstruction aims to obtain an accurate underlying geometry given a limited number of multi-view images from unseen scenes. However, existing methods select only informative and relevant views using predefined scores for training and testing phases. This constraint renders the model impractical in real-world scenarios, where the availability of favorable combinations cannot always be ensured. We introduce and validate a view-combination score to indicate the effectiveness of the input view combination. We …

arxiv cs.cv data data sets surface type view