Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Zhichao, Wang, Jianjie, Zhang, Zhixianhe, Xie, Pangu, Sheng, Xiangfei, Chen, Pengfei, Li, Leida
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908865592819712
author Yang, Zhichao
Wang, Jianjie
Zhang, Zhixianhe
Xie, Pangu
Sheng, Xiangfei
Chen, Pengfei
Li, Leida
author_facet Yang, Zhichao
Wang, Jianjie
Zhang, Zhixianhe
Xie, Pangu
Sheng, Xiangfei
Chen, Pengfei
Li, Leida
contents Image aesthetic assessment (IAA) has extensive applications in content creation, album management, and recommendation systems, etc. In such applications, it is commonly needed to pick out the most aesthetically pleasing image from a series of images with subtle aesthetic variations, a topic we refer to as fine-grained IAA. Unfortunately, state-of-the-art IAA models are typically designed for coarse-grained evaluation, where images with notable aesthetic differences are evaluated independently on an absolute scale. These models are inherently limited in discriminating fine-grained aesthetic differences. To address the dilemma, we contribute FGAesthetics, a fine-grained IAA database with 32,217 images organized into 10,028 series, which are sourced from diverse categories including Natural, AIGC, and Cropping. Annotations are collected via pairwise comparisons within each series. We also devise Series Refinement and Rank Calibration to ensure the reliability of data and labels. Based on FGAesthetics, we further propose FGAesQ, a novel IAA framework that learns discriminative aesthetic scores from relative ranks through Difference-preserved Tokenization (DiffToken), Comparative Text-assisted Alignment (CTAlign), and Rank-aware Regression (RankReg). FGAesQ enables accurate aesthetic assessment in fine-grained scenarios while still maintains competitive performance in coarse-grained evaluation. Extensive experiments and comparisons demonstrate the superiority of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2603_03907
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks
Yang, Zhichao
Wang, Jianjie
Zhang, Zhixianhe
Xie, Pangu
Sheng, Xiangfei
Chen, Pengfei
Li, Leida
Computer Vision and Pattern Recognition
Image aesthetic assessment (IAA) has extensive applications in content creation, album management, and recommendation systems, etc. In such applications, it is commonly needed to pick out the most aesthetically pleasing image from a series of images with subtle aesthetic variations, a topic we refer to as fine-grained IAA. Unfortunately, state-of-the-art IAA models are typically designed for coarse-grained evaluation, where images with notable aesthetic differences are evaluated independently on an absolute scale. These models are inherently limited in discriminating fine-grained aesthetic differences. To address the dilemma, we contribute FGAesthetics, a fine-grained IAA database with 32,217 images organized into 10,028 series, which are sourced from diverse categories including Natural, AIGC, and Cropping. Annotations are collected via pairwise comparisons within each series. We also devise Series Refinement and Rank Calibration to ensure the reliability of data and labels. Based on FGAesthetics, we further propose FGAesQ, a novel IAA framework that learns discriminative aesthetic scores from relative ranks through Difference-preserved Tokenization (DiffToken), Comparative Text-assisted Alignment (CTAlign), and Rank-aware Regression (RankReg). FGAesQ enables accurate aesthetic assessment in fine-grained scenarios while still maintains competitive performance in coarse-grained evaluation. Extensive experiments and comparisons demonstrate the superiority of the proposed method.
title Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.03907