AI RESEARCH
CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage
arXiv CS.LG
•
ArXi:2605.15597v1 Announce Type: cross Modern 3D visual learning relies on observations sampled from metric 3D assets, yet existing scans, meshes, point clouds, simulations, and reconstructions do not directly provide a sparse, comparable, and geometry-consistent panoramic