Personalized Image Aesthetics Assessment

Follow this topic Ask about this topic

The field studies how to predict an individual’s visual preferences, which can differ substantially from population-average aesthetic scores and matter for image selection, editing, and generation. Methods learn from personal ratings or pairwise rankings, elicit preferences through profiles or interviews, and use preference embeddings, vision-language models, or lightweight adaptation to personalize predictions. Evaluation includes held-out users and cross-domain settings, with datasets such as XPASS-Vis and PPR10K supporting tests of preference transfer and personalized choices. A central challenge is achieving reliable personalization from sparse feedback: unsupervised transfer can help, but still falls short of supervised performance, and preferences may shift across image domains or over time.

Latest papers

14 papers0 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

PALATE: Personalized Aesthetic Learning through Adaptive Taste Evolution for Multi-User Portrait Retouching
Aug 19, 2026Jingxuan Wang, Yifan Mei, Yuxia Niu +2Personalized Reward Modeling User Preference Modeling
Harbin Institute of Technology · MT Lab, Meitu Inc. · Xiamen University +1
Global Attention-Fused Image Cropping with Attention-Guided and Global-Aligned Crop Evaluator
Aug 5, 2026Haotian Yang, Zhile Yang, Kin-Man Lam +2Personalized Image Aesthetics Assessment Image Editing
Faculty of Data Science, City University of Macau, Macao, China · Shenzhen University of Advanced Technology, Shenzhen, China · Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China +2
DODA: A Database of Datasets for Aesthetics Research
Jul 30, 2026Lisa Koßmann, Ralf Bartho, Christoph Redies +1Personalized Image Aesthetics Assessment Dataset Discovery
Laboratory of Experimental Psychology, Department of Brain and Cognition, University of Leuven (KU Leuven), Leuven, Belgium · Leuven AI Institute, University of Leuven (KU Leuven), Leuven, Belgium · Experimental Aesthetics Group, Institute for Anatomy I, University Hospital Jena, Germany
Learning Color Grading, No Photo Sharing: Federated Aesthetic Preference Learning for Personalized Image Enhancement
Jul 30, 2026Chuanzhi Xu, Ziyuan Tao, Jean Julien KNell +5Personalized Image Aesthetics Assessment Image Enhancement
The University of Sydney · Macquarie University
Personalized Image Aesthetic Assessment via Preference-rich Sample Mining and Cohort Merging
Jul 17, 2026Zhichao Yang, Tianjiao Gu, Zhixianhe Zhang +3Personalized Image Aesthetics Assessment Image Quality Assessment
Xidian University Xi’an, China · Xidian University Xian, China
XPASS-Vis: A Dataset for Cross-Domain Personalized Image Aesthetic Assessment
Jun 14, 2026Takato Hayashi, Hiroaki Takahara, Candy Olivia Mawalim +4Personalized Image Aesthetics Assessment Cross-Domain Generalization
Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi, Ishikawa 923-1292, Japan · Communication Science Laboratories, NTT, Inc.,2026 Atsugi-shi 243-0198, Japan
Beyond Absolute Scores: Relative Edit-induced Difference for Generalizable Image Aesthetic Assessment
Jun 4, 2026Qifei Jia, Xintong Yao, Yasen Zhang +7Personalized Image Aesthetics Assessment Image Quality Assessment
Xiaomi Corporation, Beijing, China
ERNIE-Image Technical Report
May 25, 2026Jiaxiang Liu, Zhida Feng, Pengyu Zou +46Personalized Image Aesthetics Assessment Diffusion Model Distillation
Preferences Order, Ratings Anchor: From Fused Expert Aesthetic Ground Truth to Self-Distillation
May 19, 2026Yuanpei Zhao, Jie Lin, Chao Zhang +5Pairwise Preference Learning Personalized Image Aesthetics Assessment
1Sichuan University · 2NetEase Fuxi AI Lab · †Work done during an internship at NetEase Fuxi AI Lab. +1
AI Outperforms Humans in Personalized Image Aesthetics Assessment via LLM-Based Interviews and Semantic Feature Extraction
May 14, 2026Yoshia Abe, Tatsuya Daikoku, Yasuo KuniyoshiPersonalized Image Aesthetics Assessment Image Quality Assessment
Graduate School of Information Science and Technology The University of Tokyo Bunkyo-ku, Tokyo 113-8654, Japan
Enhancing Zero-shot Personalized Image Aesthetics Assessment with Profile-aware Multimodal LLM
Apr 19, 2026Chun Wang, Chenfeng Wei, Chenyang Liu +1Zero-Shot Learning Personalized Image Aesthetics Assessment
Mashang Consumer Finance Co., Ltd., Chongqing, China · Xi’an Jiaotong-Liverpool University, Suzhou, China · Beijing University of Posts and Telecommunications, Beijing, China
What Do Vision-Language Models Encode for Personalized Image Aesthetics Assessment?
Apr 13, 2026Koki Ryu, Hitomi YanakaPersonalized Image Aesthetics Assessment Vision-Language Models
The University of Tokyo · Riken · Tohoku University
Personalizing Text-to-Image Generation to Individual Taste
Apr 8, 2026Anne-Sofie Maerten, Juliane Verwiebe, Shyamgopal Karthik +3Personalized Reward Modeling Personalized Image Aesthetics Assessment
Tübingen AI Center, University of Tübingen · Department of Brain and Cognition, KU Leuven
Facial beauty prediction fusing transfer learning and broad learning system
Mar 14, 2026Junying Gan, Xiaoshan Xie, Yikui Zhai +3Personalized Image Aesthetics Assessment
Department of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China

Aug 19, 2026J/K move · Enter open · S save

PALATE: Personalized Aesthetic Learning through Adaptive Taste Evolution for Multi-User Portrait Retouching

Jingxuan Wang, Yifan Mei, Yuxia Niu, Chaowan Jiao+1

Harbin Institute of Technology · MT Lab, Meitu Inc. · Xiamen University+1

Personalized Reward Modeling User Preference Modeling Personalized Image Aesthetics Assessment Reward Modeling Image Editing Pairwise Preference Learning

Open paper AskPDF arXiv

Automatic portrait retouching has advanced rapidly, yet its objective is inherently subjective: the same portrait admits multiple professionally valid results, and users disagree about which one is best. Most existing methods optimize a population-level aesthetic standard and therefore cannot capture individual taste, while fine-tuning a separate editing model for every user incurs prohibitive training, storage, and data costs. We propose PALATE, a shared reward-evolution framework that keeps the image editor fixed and instead personalizes the selection among retouched candidates of the same source portrait. PALATE decomposes the reward for each user into a global backbone shared by all users, category-level residuals shared by aesthetically similar users, and a lightweight user adapter, with anti-collapse regularizers keeping the three levels complementary.A cyclic dual-level distillation scheme first distills user-specific preferences into category rewards and then consolidates the resulting category-level knowledge into the global backbone, which is redistributed to initialize the next evolution round. In this way, the shared initialization improves progressively across rounds, enabling unseen users to be calibrated from only a few rankings. On expert-retouched candidates from PPR10K with held-out users and held-out images, PALATE attains 72.83% pairwise preference-prediction accuracy, surpassing all reward, aesthetic, and image-quality baselines, of which the strongest, PickScore, reaches 58.06%. Each new user costs only 512 bytes of user-specific parameters and millisecond-level scoring.