Saved in:
Bibliographic Details
Main Authors: Guo, Yuxiang, Liu, Jiang, Wang, Ze, Chen, Hao, Sun, Ximeng, Zhao, Yang, Wu, Jialian, Yu, Xiaodong, Liu, Zicheng, Barsoum, Emad
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.01010
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916983048503296
author Guo, Yuxiang
Liu, Jiang
Wang, Ze
Chen, Hao
Sun, Ximeng
Zhao, Yang
Wu, Jialian
Yu, Xiaodong
Liu, Zicheng
Barsoum, Emad
author_facet Guo, Yuxiang
Liu, Jiang
Wang, Ze
Chen, Hao
Sun, Ximeng
Zhao, Yang
Wu, Jialian
Yu, Xiaodong
Liu, Zicheng
Barsoum, Emad
contents The rapid advancement of text-to-image (T2I) models has increased the need for reliable human preference modeling, a demand further amplified by recent progress in reinforcement learning for preference alignment. However, existing approaches typically quantify the quality of a generated image using a single scalar, limiting their ability to provide comprehensive and interpretable feedback on image quality. To address this, we introduce ImageDoctor, a unified multi-aspect T2I model evaluation framework that assesses image quality across four complementary dimensions: plausibility, semantic alignment, aesthetics, and overall quality. ImageDoctor also provides pixel-level flaw indicators in the form of heatmaps, which highlight misaligned or implausible regions, and can be used as a dense reward for T2I model preference alignment. Inspired by the diagnostic process, we improve the detail sensitivity and reasoning capability of ImageDoctor by introducing a "look-think-predict" paradigm, where the model first localizes potential flaws, then generates reasoning, and finally concludes the evaluation with quantitative scores. Built on top of a vision-language model and trained through a combination of supervised fine-tuning and reinforcement learning, ImageDoctor demonstrates strong alignment with human preference across multiple datasets, establishing its effectiveness as an evaluation metric. Furthermore, when used as a reward model for preference tuning, ImageDoctor significantly improves generation quality -- achieving an improvement of 10% over scalar-based reward models.
format Preprint
id arxiv_https___arxiv_org_abs_2510_01010
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning
Guo, Yuxiang
Liu, Jiang
Wang, Ze
Chen, Hao
Sun, Ximeng
Zhao, Yang
Wu, Jialian
Yu, Xiaodong
Liu, Zicheng
Barsoum, Emad
Computer Vision and Pattern Recognition
The rapid advancement of text-to-image (T2I) models has increased the need for reliable human preference modeling, a demand further amplified by recent progress in reinforcement learning for preference alignment. However, existing approaches typically quantify the quality of a generated image using a single scalar, limiting their ability to provide comprehensive and interpretable feedback on image quality. To address this, we introduce ImageDoctor, a unified multi-aspect T2I model evaluation framework that assesses image quality across four complementary dimensions: plausibility, semantic alignment, aesthetics, and overall quality. ImageDoctor also provides pixel-level flaw indicators in the form of heatmaps, which highlight misaligned or implausible regions, and can be used as a dense reward for T2I model preference alignment. Inspired by the diagnostic process, we improve the detail sensitivity and reasoning capability of ImageDoctor by introducing a "look-think-predict" paradigm, where the model first localizes potential flaws, then generates reasoning, and finally concludes the evaluation with quantitative scores. Built on top of a vision-language model and trained through a combination of supervised fine-tuning and reinforcement learning, ImageDoctor demonstrates strong alignment with human preference across multiple datasets, establishing its effectiveness as an evaluation metric. Furthermore, when used as a reward model for preference tuning, ImageDoctor significantly improves generation quality -- achieving an improvement of 10% over scalar-based reward models.
title ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.01010