Multi-view Pyramid Transformer: Look Coarser to See Broader 事件

Multi-view Pyramid Transformer: Look Coarser to See Broader arXiv:2512.07806v2 Announce Type: replace Abstract: We propose Multi-view Pyramid Transformer (MVP), a scalable multi-view transformer architecture that directly reconstructs large 3D scenes from tens to hundreds of images in a single forward pass. Drawing on the idea of ``looking broader to see the whole, looking finer to see the details," MVP is built on two core design principles: 1) a local-to-global inter-view hierarchy that gradu