Metraipolis › archive › dc_3402c4dbc548

When Depth Lies: Benchmarking Vision-Language Models on Mirror-Induced RGB-D Ambiguity — arXiv:2610.41651

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41651
License (as archived): CC0-1.0
Archived: 2026-11-02T08:03:23.111Z
SHA-256 of the archived text: 83063b2633d16695417baccf9d142ac571a2a77382fc7bc07c1eb1e839240ec2
Stable URL of this page: https://metraipolis.com/documento/dc_3402c4dbc548

How to cite

When Depth Lies: Benchmarking Vision-Language Models on Mirror-Induced RGB-D Ambiguity — arXiv:2610.41651 — arXiv (en), https://arxiv.org/abs/2610.41651 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3402c4dbc548 (Metraipolis archive dc_3402c4dbc548, sha256 83063b2633d16695417baccf9d142ac571a2a77382fc7bc07c1eb1e839240ec2)

BibTeX

@misc{dc3402c4dbc548,
  title = {When Depth Lies: Benchmarking Vision-Language Models on Mirror-Induced RGB-D Ambiguity — arXiv:2610.41651},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41651},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3402c4dbc548; sha256 83063b2633d16695417baccf9d142ac571a2a77382fc7bc07c1eb1e839240ec2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41651. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language models (VLMs) have made significant progress in spatial reasoning, particularly by integrating RGB images with depth data, which is often assumed to faithfully reflect physical distances. However, mirrors violate this assumption: they distort depth readings while reproducing object appearances, making reflections difficult to distinguish from real objects. As existing benchmarks rarely consider such reflective scenarios, VLM performance in mirror scenes remains largely unexplored. In this work, we introduce a mirror-centric RGB-D dataset from reflective scenes to evaluate the spatial reasoning capabilities of state-of-the-art VLMs in these scenarios. Specifically, we collect 1,011 RGB-D images from 525 real-world scenes, spanning diverse indoor and outdoor environments, six reflective surface types, and both daytime and nighttime conditions. All images are annotated with reflective surface region masks and mask annotations for both directly observed and mirror-reflected objects. Then, we curate a benchmark named MIRA-Bench (Mirror-Induced Reasoning Ambiguity Benchmark), comprising 14,140 QA pairs across eight sub-tasks organized into three cognitive levels: Reflection-aware Perception, Spatial Reasoning, and Scene-level Decision-making. We evaluate state-of-the-art VLMs on MIRA-Bench and find consistent failures across tasks: models misclassify whether objects are directly observed or reflected, fail to match reflected instances to their real-world counterparts, and produce erroneous spatial inferences. Remarkably, providing depth data actually degrades reasoning performance, implying that VLMs cannot identify incorrect depth in mirror scenes. The code and data are available at this https URL

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.41651 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-02T07:44:00.761Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).