Data to 7 Oct 2026

Q-Insight: Understanding Image Quality via Visual Reinforcement Learning

arXiv 2503.22679 ↗First posted 28 Mar 2025cs.CVcited by 93

Not on the map. Why?

Cited by 28 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image quality assessment (IQA) focuses on the perceptual visual quality of images, playing a crucial role in downstream tasks such as image reconstruction, compression, and generation. The rapid advancement of multi-modal large language models (MLLMs) has significantly broadened the scope of IQA, moving toward comprehensive image quality understanding that incorporates content analysis, degradation perception, and comparison reasoning beyond mere numerical scoring. Previous MLLM-based methods typically either generate numerical scores lacking interpretability or heavily rely on supervised fine-tuning (SFT) using large-scale annotated datasets to provide descriptive assessments, limiting their flexibility and applicability. In this paper, we propose Q-Insight, a reinforcement learning-based model built upon group relative policy optimization (GRPO), which demonstrates strong visual reasoning capability for image quality understanding while requiring only a limited amount of rating scores and degradation labels. By jointly optimizing score regression and degradation perception tasks with carefully designed reward functions, our approach effectively exploits their mutual benefits for enhanced performance. Extensive experiments demonstrate that Q-Insight substantially outperforms existing state-of-the-art methods in both score regression and degradation perception tasks, while exhibiting impressive zero-shot generalization to comparison reasoning tasks. Code will be available at https://github.com/lwq20020127/Q-Insight.

Key facts. Cited by 93 papers in the map (data through 7 Oct 2026). Builds on 56 of its 76 references that are in the map. First posted on arXiv 28 Mar 2025.

Builds on

56 of 76 references.

References · 56

2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
2022Training language models to follow instructions with human feedbackcited by 15,712
2017Proximal Policy Optimization Algorithmscited by 14,441
2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
2023Visual Instruction Tuningcited by 7,792
2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
2025Qwen2.5-VL Technical Reportcited by 5,418
2017Deep reinforcement learning from human preferencescited by 3,846
2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950

38 more

2024Qwen2.5-Coder Technical Reportcited by 1,151
2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,057
2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 703
2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
2025Visual-RFT: Visual Reinforcement Fine-Tuningcited by 501
2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 489
2023RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedbackcited by 404
2017NIMA: Neural Image Assessmentcited by 387
2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 351
2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 301
2025R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimizationcited by 296
2023Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Visioncited by 247
2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 224
2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimizationcited by 223
2020PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restorationcited by 177
2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learningcited by 172
2018PieAPP: Perceptual Image-Error Assessment through Pairwise Preferencecited by 158
2023Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Modelscited by 152
2017RankIQA: Learning from Rankings for No-reference Image Quality Assessmentcited by 150
2020MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessmentcited by 144
2016Learning a No-Reference Quality Metric for Single-Image Super-Resolutioncited by 143
2023AGIQA-3K: An Open Database for AI-Generated Image Quality Assessmentcited by 142
2025Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distributioncited by 139
2024InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoningcited by 117
2023Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Modelscited by 104
2024Towards Open-ended Visual Quality Comparisoncited by 85
2024o1-Coder: an o1 Replication for Codingcited by 77
2024Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Comparecited by 66
2022Shift-tolerant Perceptual Similarity Metriccited by 44
2021GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessmentcited by 43
2021Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessmentcited by 41
2024An Intelligent Agentic System for Complex Image Restoration Problemscited by 41
2024Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMscited by 39
2024Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Datasetcited by 38
2025Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumptioncited by 34

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 41; 2026: 52.

93 papers.

Sort:

By area:

38 more

50 most cited of 93 All 93 (JSON)

Similar, not cited

Close in wording, no citation either way