SOURCE-LINKED INTELLIGENCE

When Wider Views Fail: Stress-Testing Feed-Forward 3D Reconstruction

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Feed-forward 3D reconstruction models enable efficient geometry estimation from sparse images, but their pretrained nature can make them vulnerable to distribution shifts beyond their training data. Identifying these failure modes is important for understanding when such models can be reliably deployed in unconstrained imaging settings. We investigate viewpoint variation as a controlled distribution shift by varying the angular span of sparse image inputs while keeping the input budget fixed. Across multiple feed-forward reconstruction models, we observe substantial degradation as viewpoint sp

Read original source ↗ Open in workspace

recordType

paper

region

Global