arXiv cs.AI· Siddharth Vohra, Min Xu·· 23 小时前AI 评分52
Know When to Zoom:视觉语言模型能看清多小的细节?
Know When to Zoom: How Small Is Too Small for Vision-Language Models?
AI 导读
论文测量了四家厂商七个视觉语言模型在大图上的细节保留情况,模型能稳定读出的最小文字从 6 像素以下升至 7680×4320 照片默认设置下的 10 至 13 像素。
正文 · 原文
Abstract:Online vision-language models often miss small details in large images, because the service shrinks the image, or rejects it, before the model ever sees it. A car 20 pixels wide in an 8000 by 6000 drone photo reaches Claude about 6 pixels wide, and OpenAI's default rejects the photo outright. We measure how much detail survives for seven models from four vendors, using an eye exam of printed codes and 601 questions about small objects in real photos. The smallest text a model reads half the time grows from 6 pixels or less on a small image to a predicted 10 to 13 pixels on a 7680 by 4320 photo at default settings. Zooming wins much of the detail back. Splitting each photo into up to nine tiles raises accuracy by 11.1 to 14.5 percentage points for Claude and Gemini, and by avoiding rejections it lifts GPT-6.1 Sol from 50.7% to 83.7%. A two-step zoom, in which the model first names the region it needs, matches or beats tiles on Gemini and comes within 2.5 points of them on Claude, with about 40% of their image tokens. When a detail is lost, Claude and Gemini both say they cannot tell about half the time, but they fail differently in the rest: Gemini gives a confident wrong answer in 43% to 48% of these cases, Claude in only 5% to 9%. A check based on detail size, run before the call, misses most of the gain from tiles on Claude and Gemini, but Claude's own reply is a reliable trigger: tiling only after an unsure reply comes within 1.4 points of always tiling with 62% to 70% of the image tokens. We turn these findings into five rules for when an agent should zoom, and release the eye exam, every model answer and code at this https URL.
| Comments: | Accepted to the SENSE workshop at WACV 2027. 10 pages, 5 figures, 3 tables. Code, data and a plain-language walkthrough: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.22709 [cs.CV] |
| (or arXiv:2611.22709v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22709 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Siddharth Vohra [view email]
[v1]
Tue, 17 Nov 2026 12:50:14 UTC (179 KB)
来源:arXiv cs.AI · arxiv.org