GrapeSplat: Geometry-Grounded Reconstruction via Amalgamated Pose-Free Encoding for Feed-Forward 3D Gaussian Splatting
GrapeSplat amalgamates multi-view cues into a voxel-aligned scene representation and decodes Gaussians directly from the learned grid, requiring no per-scene optimization or post-processing.
Si-Yu Lu, Yung-Yao Chen, Yi-Jan Chen et al.
· 0 citations