Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.15423 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915681958625280 |
|---|---|
| author | Nguyen, Hoang Xu, Xiaohao Huang, Xiaonan |
| author_facet | Nguyen, Hoang Xu, Xiaohao Huang, Xiaonan |
| contents | 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 geometrically planar but perceptually ambiguous inputs. We term this failure the 3D Mirage. This paper introduces the first end-to-end framework to probe, quantify, and tame this unquantified safety risk. To probe, we present 3D-Mirage, the first benchmark of real-world illusions (e.g., street art) with precise planar-region annotations and context-restricted crops. To quantify, we propose a Laplacian-based evaluation framework with two metrics: the Deviation Composite Score (DCS) for spurious non-planarity and the Confusion Composite Score (CCS) for contextual instability. To tame this failure, we introduce Grounded Self-Distillation, a parameter-efficient strategy that surgically enforces planarity on illusion ROIs while using a frozen teacher to preserve background knowledge, thus avoiding catastrophic forgetting. Our work provides the essential tools to diagnose and mitigate this phenomenon, urging a necessary shift in MDE evaluation from pixel-wise accuracy to structural and contextual robustness. Our code and benchmark will be publicly available to foster this exciting research direction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_15423 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Photorealistic Phantom Roads in Real Scenes: Disentangling 3D Hallucinations from Physical Geometry Nguyen, Hoang Xu, Xiaohao Huang, Xiaonan Computer Vision and Pattern Recognition Robotics 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 geometrically planar but perceptually ambiguous inputs. We term this failure the 3D Mirage. This paper introduces the first end-to-end framework to probe, quantify, and tame this unquantified safety risk. To probe, we present 3D-Mirage, the first benchmark of real-world illusions (e.g., street art) with precise planar-region annotations and context-restricted crops. To quantify, we propose a Laplacian-based evaluation framework with two metrics: the Deviation Composite Score (DCS) for spurious non-planarity and the Confusion Composite Score (CCS) for contextual instability. To tame this failure, we introduce Grounded Self-Distillation, a parameter-efficient strategy that surgically enforces planarity on illusion ROIs while using a frozen teacher to preserve background knowledge, thus avoiding catastrophic forgetting. Our work provides the essential tools to diagnose and mitigate this phenomenon, urging a necessary shift in MDE evaluation from pixel-wise accuracy to structural and contextual robustness. Our code and benchmark will be publicly available to foster this exciting research direction. |
| title | Photorealistic Phantom Roads in Real Scenes: Disentangling 3D Hallucinations from Physical Geometry |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2512.15423 |