With collective endeavors, multimodal large language models (MLLMs) are undergoing a flourishing development. However, their performances on image aesthetics perception remain indeterminate, which is highly desired in real-world applications. An obvious obstacle lies in the absence of a specific benchmark to evaluate the effectiveness of MLLMs on aesthetic perception. This blind groping may impede the further development of more advanced MLLMs with aesthetic perception capacity. To address this dilemma, we propose AesBench, an expert benchmark aiming to comprehensively evaluate the aesthetic perception capacities of MLLMs through elaborate design across dual facets. (1) We construct an Expert-labeled Aesthetics Perception Database (EAPD), which features diversified image contents and high-quality annotations provided by professional aesthetic experts. (2) We propose a set of integrative criteria to measure the aesthetic perception abilities of MLLMs from four perspectives, including Perception (AesP), Empathy (AesE), Assessment (AesA) and Interpretation (AesI). Extensive experimental results underscore that the current MLLMs only possess rudimentary aesthetic perception ability, and there is still a significant gap between MLLMs and humans. We hope this work can inspire the community to engage in deeper explorations on the aesthetic potentials of MLLMs. Source data will be available at https://github.com/yipoh/AesBench.
AesTest: Measuring Aesthetic Intelligence from Perception to Production
University of International Business and Economics(国际商务经济大学);University of Science and Technology of China(中国科学技术大学);Huawei Technologies Co., Ltd(华为技术有限公司);Beijing Electronic Science and Technology Institute(北京电子科技研究所);Beijing Institute for General Artificial Intelligence(北京通用人工智能研究院)
HCSU: A Dataset and Benchmark for Fine-Grained Historical Calligraphy Style Understanding
School of Computer Science and Technology, Tongji University(同济大学计算机科学与技术学院);The Key Laboratory of Embedded System and Service Computing, Ministry of Education(教育部嵌入式系统与服务计算重点实验室)
An Evolutionary Agentic Approach for Open-ended Image Quality Perception
New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所模式识别国家重点实验室);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);The Hong Kong University of Science and Technology(香港科技大学);Transsion(传音)
Learning to Look before Learning to Like: Incorporating Human Visual Cognition into Aesthetic Quality Assessment
Faculty of Data Science, City University of Macau(澳门城市大学数据科学学院);Zhongshan Ophthalmic Center, Sun Yat-sen University(中山眼科中心,中山大学);School of computer science, Torrens University Australia(计算机科学学院,托伦斯大学澳大利亚分校)
Using Multimodal Deep Neural Networks to Disentangle Language from Visual Aesthetics
Harvard University(哈佛大学);Harvard School of Public Health(哈佛公共卫生学院);Massachusetts General Hospital(麻省总医院);Massachusetts Institute of Technology(麻省理工学院);Johns Hopkins University(约翰斯·霍普金斯大学)
Vision Transformer attention alignment with human visual perception in aesthetic object evaluation
Escuela de Informática y Telecomunicaciones, Universidad Diego Portáles(戴维·波特莱斯大学信息与电信学院);Department of Specific Didactics, University of Cordoba(科尔多瓦大学特定教学系);Facultad de Ingeniería y Ciencias, Universidad Adolfo Ibáñez(阿道弗·伊巴涅斯大学工程与科学学院)
本文通过眼动实验与 DINO 预训练 ViT 的注意图对比,发现特定注意头和高斯参数下可较好对齐人类审美视觉注意。
UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院,清华大学);Media Analytics and Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University(媒体分析与计算实验室,人工智能系,厦门大学);School of Computer Science and Technology, Ocean University of China(计算机科学与技术学院,中国海洋大学);Institute of Image Communication and Information Processing, Shanghai Jiao Tong University(图像通信与信息处理研究所,上海交通大学)
Texture or Semantics? Vision-Language Models Get Lost in Font Recognition
University of California, San Diego(加州大学圣地亚哥分校);ByteDance(字节跳动);The University of Queensland(昆士兰大学);University of Southern California(南加州大学);University at Buffalo(布法罗大学);University of California, Merced(加州大学默塞德分校)
An End-to-End Neural Network for Image Cropping by Learning Composition from Aesthetic Photos
School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China(中国北京邮电大学计算机学院);Information Sciences Institute, University of Southern California, Marina del Rey, CA, USA(美国加利福尼亚州马里纳德尔雷伊南加州大学信息科学研究所)
SVGEval: A Vision-Grounded Framework for Perceptual-Quality Benchmarking and Evaluation in Text-to-SVG Generation
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东省人工智能与数字经济实验室(深圳));School of Integrated Circuits (School of Information Science and Electronic Engineering), Shanghai Jiao Tong University(上海交通大学集成电路学院(信息科学与工程学院));Zhiyuan College, Shanghai Jiao Tong University(上海交通大学致远学院)
VULCA-Bench: A Multicultural Vision-Language Benchmark for Evaluating Cultural Understanding
DJCAD, University of Dundee, United Kingdom(邓迪大学DJCAD部门);University of California, Santa Cruz, USA(加州大学圣克ruz分校);Analogy AI;East China Normal University, China(华东师范大学);Nanjing University, China(南京大学);Department of Mechanical Engineering, School of Engineering, University of Birmingham(伯明翰大学工程学院机械工程系)
GalleryGPT: Analyzing Paintings with Large Multimodal Models
Tongji University(同济大学);National University of Singapore(新加坡国立大学);University of Electronic Science and Technology of China(电子科技大学);The Hong Kong Polytechnic University(香港理工大学);Singapore University of Technology and Design(新加坡科技设计大学)