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

2026-09-21

AI Summary

研究通过改变视角范围测试了前馈3D重建模型在不同视角下的性能，发现随着视角范围的增加，模型表现显著下降，揭示了这些模型在面对分布偏移时的脆弱性。

Abstract

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 span increases, with wide spans producing both incomplete surface coverage and geometry unsupported by the observed imagery. These results reveal that viewpoint variation can induce failure modes beyond conventional reconstruction incompleteness, highlighting the need to evaluate pretrained feed-forward models under distribution shifts that challenge their learned geometric priors.

Problem

• feed-forward 3D reconstruction
• viewpoint variation
• distribution shift
• geometry estimation

Innovation

• viewpoint variation
• feed-forward 3D reconstruction
• distribution shifts
• geometric priors