Metraipolis › archive › dc_72fcf48a1374

SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility Conditions — arXiv:2609.31823

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31823
License (as archived)
CC0-1.0
Archived
2026-10-07T20:59:34.626Z
SHA-256 of the archived text
02fa934791ed4818f7f0e62d05e24f4242796c511df0db54d1dbc098ef736d8a
Stable URL of this page
https://metraipolis.com/documento/dc_72fcf48a1374

How to cite

SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility Conditions — arXiv:2609.31823 — arXiv (en), https://arxiv.org/abs/2609.31823 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72fcf48a1374 (Metraipolis archive dc_72fcf48a1374, sha256 02fa934791ed4818f7f0e62d05e24f4242796c511df0db54d1dbc098ef736d8a)
BibTeX
@misc{dc72fcf48a1374,
  title = {SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility Conditions — arXiv:2609.31823},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31823},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72fcf48a1374; sha256 02fa934791ed4818f7f0e62d05e24f4242796c511df0db54d1dbc098ef736d8a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31823. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large vision-language models (LVLMs) have demonstrated remarkable performance on multimodal reasoning benchmarks, yet their perceptual reliability under physically constrained imaging conditions remains poorly understood. Existing evaluations predominantly assume ideal visual inputs and therefore fail to characterize how camera distance, illumination, viewpoint, and pixel density fundamentally affect semantic recoverability. We introduce SynDORBench, the first physically grounded benchmark for evaluating LVLM perceptual robustness under DORI-calibrated conditions aligned with human visual capability standards. SynDORBench comprises over 54k question--answer pairs generated through a controllable synthetic pipeline that systematically varies viewing distance, lighting, camera geometry, and action pose according to physically interpretable pixel-density regimes. To support scalable low-visibility supervision, we further propose a discernibility annotation framework that propagates human perceptual labels using mask-conditioned statistical features and ensemble learning. We evaluate 16 open-source LVLMs, a commercial LVLM baseline, and YOLO11x across human-presence classification and action recognition tasks under progressively degraded visibility conditions. Our results reveal that perceptual failure in LVLMs is strongly governed by pixel density and physical imaging constraints rather than model scale alone. Surprisingly, several compact open-source LVLMs outperform larger commercial baselines and substantially exceed YOLO11x robustness under long-range and low-light conditions. SynDORBench establishes a new benchmark paradigm for physically grounded multimodal evaluation, enabling systematic analysis of LVLM reliability under real-world perceptual constraints and direct comparison against human visibility thresholds.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.31823 — 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 2026-10-07T20:29:02.156Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).