AI RESEARCH
SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion
arXiv CS.LG
•
ArXi:2605.01466v1 Announce Type: cross Although multi-modal learning has advanced point cloud completion, the theoretical mechanisms remain unclear. Recent works attribute success to the connection between modalities, yet we identify that standard hard projection severs this connection: projecting a sparse point cloud onto the image plane yields an extremely sparse, which hinders visual prior propagation, a failure mode we term Cross-Modal Entropy Collapse.