PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar

arXiv:2312.14239v2 Announce Type: replace
Abstract: 3D reconstruction from a single-view is challenging because of the ambiguity from monocular cues and lack of information about occluded regions. Neural radiance fields (NeRF), while popular for view synthesis and 3D reconstruction, are typically reliant on multi-view images. Existing methods for single-view 3D reconstruction with NeRF rely on either data priors to hallucinate views of occluded regions, which may not be physically accurate, or shadows observed by RGB cameras, which are difficult to detect …

3d reconstruction abstract arxiv cs.cv eess.iv fields images information lidar nerf neural radiance fields popular synthesis type via view