mlsanityData to 14 Oct 2026

VisualCritic: Making LMMs Perceive Visual Quality Like Humans

arXiv 2403.12806 ↗First posted 19 Mar 2024cs.CVcited by 13

On the map: Multimodal LLMs / vision-language models → Image editing and quality assessment

Abstract (arXiv)

At present, large multimodal models (LMMs) have exhibited impressive generalization capabilities in understanding and generating visual signals. However, they currently still lack sufficient capability to perceive low-level visual quality akin to human perception. Can LMMs achieve this and show the same degree of generalization in this regard? If so, not only could the versatility of LMMs be further enhanced, but also the challenge of poor cross-dataset performance in the field of visual quality assessment could be addressed. In this paper, we explore this question and provide the answer "Yes!". As the result of this initial exploration, we present VisualCritic, the first LMM for broad-spectrum image subjective quality assessment. VisualCritic can be used across diverse data right out of box, without any requirements of dataset-specific adaptation operations like conventional specialist models. As an instruction-following LMM, VisualCritic enables new capabilities of (1) quantitatively measuring the perceptual quality of given images in terms of their Mean Opinion Score (MOS), noisiness, colorfulness, sharpness, and other numerical indicators, (2) qualitatively evaluating visual quality and providing explainable descriptions, (3) discerning whether a given image is AI-generated or photographic. Extensive experiments demonstrate the efficacy of VisualCritic by comparing it with other open-source LMMs and conventional specialist models over both AI-generated and photographic images.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in Image editing and quality assessment, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 49 of its 68 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

49 of 68 references.

References · 49

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  6. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  7. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  8. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  9. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  10. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  11. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,089
  12. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
37 more
  1. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,040
  2. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  3. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 906
  4. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 691
  5. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 681
  6. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 640
  7. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 625
  8. 2023Otter: A Multi-Modal Model with In-Context Instruction Tuningcited by 550
  9. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 517
  10. 2023Ferret: Refer and Ground Anything Anywhere at Any Granularitycited by 509
  11. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 355
  12. 2023OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documentscited by 316
  13. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 302
  14. 2023InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Compositioncited by 297
  15. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 280
  16. 2023Generating Images with Multimodal Language Modelscited by 260
  17. 2021ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learningcited by 256
  18. 2023Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Visioncited by 249
  19. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 223
  20. 2015Massive Online Crowdsourced Study of Subjective and Objective Picture Qualitycited by 209
  21. 2023Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuningcited by 170
  22. 2017RankIQA: Learning from Rankings for No-reference Image Quality Assessmentcited by 151
  23. 2020MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessmentcited by 144
  24. 2023AGIQA-3K: An Open Database for AI-Generated Image Quality Assessmentcited by 142
  25. 2023Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wildcited by 97
  26. 2023KOSMOS-2.5: A Multimodal Literate Modelcited by 96
  27. 2021Image Quality Assessment using Contrastive Learningcited by 95
  28. 2020Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Trainingcited by 72
  29. 2023AIGCIQA2023: A Large-scale Image Quality Assessment Database for AI Generated Images: from the Perspectives of Quality, Authenticity and Correspondencecited by 61
  30. 2022Shift-tolerant Perceptual Similarity Metriccited by 44
  31. 2021GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessmentcited by 43
  32. 2023Subjective and Objective Quality Assessment for in-the-Wild Computer Graphics Imagescited by 21
  33. 2023DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Designcited by 17
  34. 2023Responsible Task Automation: Empowering Large Language Models as Responsible Task Automatorscited by 14
  35. 2023Test Time Adaptation for Blind Image Quality Assessmentcited by 11
  36. 2022Source-free Unsupervised Domain Adaptation for Blind Image Quality Assessmentcited by 9
  37. 2022Content-Diverse Comparisons improve IQAcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 6; 2025: 7.

13 papers.

Sort:

By area:

  1. 2024Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Comparecited by 66
  2. 2024Quality Assessment in the Era of Large Models: A Surveycited by 26
  3. 2025Phi-Ground Tech Report: Advancing Perception in GUI Groundingcited by 25
  4. 2024LMM-PCQA: Assisting Point Cloud Quality Assessment with LMMcited by 19
  5. 2024Enhancing Blind Video Quality Assessment with Rich Quality-aware Featurescited by 19
  6. 2025Visual Text Processing: A Comprehensive Review and Unified Evaluationcited by 19
  7. 2024HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluatorcited by 13
  8. 2025The Photographer Eye: Teaching Multimodal Large Language Models to Understand Image Aesthetics like Photographerscited by 13
  9. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  10. 2025Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Modelcited by 12
  11. 2024Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunitiescited by 3
  12. 2025ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Imagescited by 2
1 more
  1. 2025Score2Instruct: Scaling Up Video Quality-Centric Instructions via Automated Dimension Scoringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards Open-ended Visual Quality Comparison
  2. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels
  3. 2025VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models: Methods and Results
  4. 2026Evaluating Vision-Language Models for Image Quality Assessment using Psychophysical Data
  5. 2025What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment
  6. 2024A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment
  7. 2026VideoAesBench: Benchmarking the Video Aesthetics Perception Capabilities of Large Multimodal Models
  8. 2026Enhancing Image Quality Assessment Ability of LMMs via Retrieval-Augmented Generation