AI RESEARCH
Learning Fine-Grained Geometry for Sparse-View Splatting via Cascade Depth Loss
arXiv CS.CV
•
ArXi:2505.22279v2 Announce Type: replace Novel view synthesis is a fundamental task in 3D computer vision that aims to reconstruct photorealistic images from novel viewpoints given a set of posed images. However, reconstruction quality degrades sharply under sparse-view conditions due to insufficient geometric cues. Existing methods, including Neural Radiance Fields (NeRF) and recent 3D Gaussian Splatting (3DGS), often exhibit blurred details and structural artifacts when trained from sparse observations.