CVPR Findings2026
Open World Image Aesthetic Assessment
Mingxiang Liao, Tianren Ma, Xijin Zhang
Abstract
Question: What is your aesthetic rating for this image?
Question: What is your aesthetic rating for this image? Theme: "Digital Glitch". Definition: Glitch glitch art is the aesthetic use of technical errors.
Justification: This image is intentionally blurry, distorted, and the colors are heavily altered.
Justification: This image is an excellent example of the "Digital Glitch" aesthetic, effectively using strong color separation and pixelated artifacts as purposeful artistic elements to create a visually striking piece.
World IAA Model Classic IAA Model Classic IAA with Single, Static Criterion Open World IAA with Pluralistic, Open Criteria Generic Score: 3.5 / 10 Theme-specific Score: 9.0 / 10 Classic Themes Non-Classic Themes User-customized Themes (a)
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on22
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- ImageReward: Learning and Evaluating Human Preferences for Text-to-Image GenerationJiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong et al.NeurIPS 2023 · 1,310 citations
- Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined LevelsHaoning Wu, Zicheng Zhang, Weixia Zhang, Chaofeng Chen et al.ICML 2024 · 499 citations
- Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level VisionHaoning Wu, Zicheng Zhang, Erli Zhang, Chaofeng Chen et al.ICLR 2024 · 258 citations
- TTRL: Test-Time Reinforcement LearningYuxin Zuo, Kaiyan Zhang, Li Sheng, Shang Qu et al.NeurIPS 2025 · 249 citations
Related papers
- Light Source Separation and Intrinsic Image Decomposition under AC IlluminationYusaku Yoshida, Ryo Kawahara, Takahiro OkabeCVPR 2023
- Towards Artistic Image Aesthetics Assessment: a Large-scale Dataset and a New MethodRan Yi, Haoyuan Tian, Zhihao Gu, Yu-Kun Lai et al.CVPR 2023
- Tap, Scan, Exploit: The Hidden Vulnerabilities of Everyday QR CodesAshish Kumar, Aarthi S, Akshay AgarwalCVPR Findings 2026 · 1 citation
- DPGF-Net: Dual-Prior Guided Fusion Network for Joint Assessment of Perceptual Quality and Semantic Consistency in AI-Generated ImagesTao Li, Xingran Liao, Mingliang ZhouCVPR 2026
- Thinking Image Color Aesthetics Assessment: Models, Datasets and BenchmarksShuai He, Anlong Ming, Yaqi Li, Jinyuan Sun et al.ICCV 2023 · 36 citations
