Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence Paper • 2505.23747 • Published about 19 hours ago • 39
ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model Paper • 2408.16767 • Published Aug 29, 2024 • 33
Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion Paper • 2406.04338 • Published Jun 6, 2024 • 40