AI RESEARCH
Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself
arXiv CS.CV
•
ArXi:2604.14048v1 Announce Type: new Feed-forward 3D reconstruction models are efficient but rigid: once trained, they perform inference in a zero-shot manner and cannot adapt to the test scene. As a result, visually plausible reconstructions often contain errors, particularly under occlusions, specularities, and ambiguous cues. To address this, we