ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning

• URL: http://arxiv.org/abs/2510.01010v1
• Date: Wed, 01 Oct 2025 15:15:55 GMT
• Title: ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning
• Authors: Yuxiang Guo, Jiang Liu, Ze Wang, Hao Chen, Ximeng Sun, Yang Zhao, Jialian Wu, Xiaodong Yu, Zicheng Liu, Emad Barsoum,
• Abstract summary: ImageDoctor is a unified multi-aspect T2I model evaluation framework.<n>It assesses image quality across four complementary dimensions: plausibility, semantic alignment, aesthetics, and overall quality.<n>ImageDoctor also provides pixel-level flaw indicators in the form of heatmaps.
• Score: 27.487909813142796
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Adaptive Contrast Adjustment Module: A Clinically-Inspired Plug-and-Play Approach for Enhanced Fetal Plane Classification [4.501187731017252]
  We propose a plug-and-play adaptive contrast adjustment module inspired by the clinical practice of doctors adjusting image contrast to obtain clearer and more discriminative structural information.<n>The module consistently improves performance across diverse models, with accuracy of lightweight models increasing by 2.02 percent, accuracy of traditional models increasing by 1.29 percent, and accuracy of state-of-the-art models increasing by 1.15 percent.<n>This approach effectively bridges low-level image features with high-level semantics, establishing a new paradigm for medical image analysis under real-world image quality variations.
  arXiv  Detail & Related papers  (2025-08-31T11:46:51Z)
• Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment [63.823383517957986]
  We propose a novel evaluation score, ICT (Image-Contained-Text) score, that achieves and surpasses the objectives of text-image alignment.<n>We further train an HP (High-Preference) score model using solely the image modality to enhance image aesthetics and detail quality.
  arXiv  Detail & Related papers  (2025-07-25T07:01:50Z)
• OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation [23.05106664412349]
  Text-to-image (T2I) models have garnered significant attention for generating high-quality images aligned with text prompts.<n>OneIG-Bench is a benchmark framework for evaluation of T2I models across multiple dimensions.
  arXiv  Detail & Related papers  (2025-06-09T17:50:21Z)
• Advancing AI-Powered Medical Image Synthesis: Insights from MedVQA-GI Challenge Using CLIP, Fine-Tuned Stable Diffusion, and Dream-Booth + LoRA [3.290817968509798]
  The MEDVQA-GI challenge addresses the integration of AI-driven text-to-image generative models in medical diagnostics.<n>This study introduces a novel approach based on fine-tuned generative models to generate dynamic, scalable, and precise images from textual descriptions.<n>Our system integrates Stable Diffusion and DreamBooth models, as well as Low-Rank Adaptation (LORA) to generate high-fidelity medical images.
  arXiv  Detail & Related papers  (2025-02-28T02:49:45Z)
• DiffDoctor: Diagnosing Image Diffusion Models Before Treating [57.82359018425674]
  We propose DiffDoctor, a two-stage pipeline to assist image diffusion models in generating fewer artifacts.<n>We collect a dataset of over 1M flawed synthesized images and set up an efficient human-in-the-loop annotation process.<n>The learned artifact detector is then involved in the second stage to optimize the diffusion model by providing pixel-level feedback.
  arXiv  Detail & Related papers  (2025-01-21T18:56:41Z)
• Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models [54.052963634384945]
  We introduce the Image Regeneration task to assess text-to-image models. We use GPT4V to bridge the gap between the reference image and the text input for the T2I model. We also present ImageRepainter framework to enhance the quality of generated images.
  arXiv  Detail & Related papers  (2024-11-14T13:52:43Z)
• PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference [62.72779589895124]
  We make the first attempt to align diffusion models for image inpainting with human aesthetic standards via a reinforcement learning framework. We train a reward model with a dataset we construct, consisting of nearly 51,000 images annotated with human preferences. Experiments on inpainting comparison and downstream tasks, such as image extension and 3D reconstruction, demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2024-10-29T11:49:39Z)
• G-Refine: A General Quality Refiner for Text-to-Image Generation [74.16137826891827]
  We introduce G-Refine, a general image quality refiner designed to enhance low-quality images without compromising integrity of high-quality ones. The model is composed of three interconnected modules: a perception quality indicator, an alignment quality indicator, and a general quality enhancement module. Extensive experimentation reveals that AIGIs after G-Refine outperform in 10+ quality metrics across 4 databases.
  arXiv  Detail & Related papers  (2024-04-29T00:54:38Z)
• Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domains [3.8137985834223502]
  Building generative models for medical images that faithfully depict clinical context may help alleviate the paucity of healthcare datasets. We explore the sub-components of the Stable Diffusion pipeline to fine-tune the model to generate medical images. Our best-performing model improves upon the stable diffusion baseline and can be conditioned to insert a realistic-looking abnormality on a synthetic radiology image.
  arXiv  Detail & Related papers  (2022-10-09T01:43:08Z)
• Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network [92.01145655155374]
  We present an unsupervised image enhancement generative network (UEGAN) It learns the corresponding image-to-image mapping from a set of images with desired characteristics in an unsupervised manner. Results show that the proposed model effectively improves the aesthetic quality of images.
  arXiv  Detail & Related papers  (2020-12-30T03:22:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.