Multi-view perceptionExpert
Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis
This preprint introduces SNAP, a self-supervised encoder-decoder transformer that learns transferable geometric scene representations from novel-view synthesis without dense 3D labels. The headline result is that SNAP matches or beats self-supervised baselines on five geometry tasks and approaches heavily geometry-supervised models such as VGGT, while staying robust to camera shifts in robot manipulation. This matters because it shows posed RGB video may replace expensive 3D annotation for spatial foundation models.