Introduces a robustness benchmark for multiview 3D consistency and COLMAP-based metrics that better detect hallucinations in 3D foundation models than existing neural metrics.
Learned 3D backbones predict geometry, cameras, and correspondences together, so their matches are already tied to the model’s own reconstruction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate
Introduces a robustness benchmark for multiview 3D consistency and COLMAP-based metrics that better detect hallucinations in 3D foundation models than existing neural metrics.