Q-Probe：通过上下文感知的智能体探测将图像质量评估扩展至高分率

Electrical Engineering and Systems Science > Image and Video Processing arXiv:2601.15356 (eess) [Submitted on 21 Jan 2026 (v1), last revised 25 Sep 2026 (this version, v6)] Title:Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing Authors:Xiang Li, Xueheng Li, Yu Wang, Xuanhua He, Zhangchi Hu, Chengjun Xie View a PDF of the paper titled Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing, by Xiang Li and 5 other authors View PDF HTML (experimental) Abstract:Reinforcement Learning (RL) has empowered Multimodal Large Language Models (MLLMs) to achieve superior human preference alignment in Image Quality Assessment (IQA). However, existing RL-based IQA models typically rely on coarse-grained global views, failing to capture subtle local degradations in high-resolution scenarios. While emerging "Thinking with Images" paradigms enable multi-scale visual perception via zoom-in mechanisms, their direct adaptation to IQA induces spurious "cropping-implies-degradation" biases and misinterprets natural depth-of-field as artifacts. To address these challenges, we propose Q-Probe, the first agentic IQA framework designed to scale IQA to high resolution via context-aware probing. First, we construct Vista-Bench, a pioneering benchmark tailored for fine-grained local degradation analysis in high-resolution IQA settings. Furthermore, we propose a three-stage training paradigm that progressively aligns the model with human preferences, while simultaneously eliminating causal bias through a novel context-aware cropping strategy. Extensive experiments demonstrate that Q-Probe achieves state-of-the-art performance in high-resolution settings while maintaining superior efficacy across resolution scales. Comments: Subjects: Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI) Cite as: arXiv:2601.15356 [eess.IV] (or arXiv:2601.15356v6 [eess.IV] for this version) https://doi.org/10.48550/arXiv.2601.15356 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Xiang Li [view email] [v1] Wed, 21 Jan 2026 08:02:32 UTC (45,246 KB) [v2] Tue, 27 Jan 2026 03:25:24 UTC (45,247 KB) [v3] Wed, 8 Apr 2026 10:30:21 UTC (45,247 KB) [v4] Thu, 9 Apr 2026 07:04:16 UTC (45,247 KB) [v5] Fri, 8 May 2026 05:52:31 UTC (9,760 KB) [v6] Fri, 25 Sep 2026 13:53:08 UTC (9,769 KB) Full-text links: Access Paper: View a PDF of the paper titled Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing, by Xiang Li and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: eess.IV new | recent | 2026-01 Change to browse by: cs cs.AI eess References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)