arXiv cs.CV
· Papers
The 3D Mirage: Probing and Taming 3D Hallucinations
arXiv:2512.15423v2 Announce Type: replace Abstract: Monocular depth foundation models achieve remarkable generalization by learning large-scale semantic priors, but this creates a critical vulnerability: they hallucinate illusory 3D structures from planar/low-curvature but perceptually ambiguous inputs. We term this fa