Agentic Retoucher for Text-To-Image Generation

• URL: http://arxiv.org/abs/2601.02046v2
• Date: Thu, 08 Jan 2026 10:57:37 GMT
• Title: Agentic Retoucher for Text-To-Image Generation
• Authors: Shaocheng Shen, Jianfeng Liang, Chunlei Cai, Cong Geng, Huiyu Duan, Xiaoyun Zhang, Qiang Hu, Guangtao Zhai,
• Abstract summary: Agentic Retoucher is a hierarchical decision-driven framework that reformulates post-generation correction as a human-like perception-reasoning-action loop.<n>This design integrates perceptual evidence, linguistic reasoning, and controllable correction into a unified, self-corrective decision process.<n>Experiments demonstrate that Agentic Retoucher consistently outperforms state-of-the-art methods in perceptual quality, distortion localization and human preference alignment.
• Score: 48.80766311858762
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-image (T2I) diffusion models such as SDXL and FLUX have achieved impressive photorealism, yet small-scale distortions remain pervasive in limbs, face, text and so on. Existing refinement approaches either perform costly iterative re-generation or rely on vision-language models (VLMs) with weak spatial grounding, leading to semantic drift and unreliable local edits. To close this gap, we propose Agentic Retoucher, a hierarchical decision-driven framework that reformulates post-generation correction as a human-like perception-reasoning-action loop. Specifically, we design (1) a perception agent that learns contextual saliency for fine-grained distortion localization under text-image consistency cues, (2) a reasoning agent that performs human-aligned inferential diagnosis via progressive preference alignment, and (3) an action agent that adaptively plans localized inpainting guided by user preference. This design integrates perceptual evidence, linguistic reasoning, and controllable correction into a unified, self-corrective decision process. To enable fine-grained supervision and quantitative evaluation, we further construct GenBlemish-27K, a dataset of 6K T2I images with 27K annotated artifact regions across 12 categories. Extensive experiments demonstrate that Agentic Retoucher consistently outperforms state-of-the-art methods in perceptual quality, distortion localization and human preference alignment, establishing a new paradigm for self-corrective and perceptually reliable T2I generation.

Related papers

• Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing [62.94394079771687]
  A burgeoning trend is to adopt high-dimensional features from representation encoders as generative latents.<n>We propose a systematic framework to adapt understanding-oriented encoder features for generative tasks.<n>We show that our approach achieves state-of-the-art reconstruction, faster convergence, and substantial performance gains in both Text-to-Image (T2I) and image editing tasks.
  arXiv  Detail & Related papers  (2025-12-19T18:59:57Z)
• INSIGHT: An Interpretable Neural Vision-Language Framework for Reasoning of Generative Artifacts [0.0]
  Current forensic systems degrade sharply under real-world conditions.<n>Most detectors operate as opaques, offering little insight into why an image is flagged as synthetic.<n>We introduce INSIGHT, a unified framework for robust detection and transparent explanation of AI-generated images.
  arXiv  Detail & Related papers  (2025-11-27T11:43:50Z)
• Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers [55.15722080205737]
  Edit2Perceive is a unified diffusion framework that adapts editing models for depth, normal, and matting.<n>Our single-step deterministic inference yields up to faster runtime while training on relatively small datasets.
  arXiv  Detail & Related papers  (2025-11-24T01:13:51Z)
• Enhancing CLIP Robustness via Cross-Modality Alignment [54.01929554563447]
  We propose Cross-modality Alignment, an optimal transport-based framework for vision-language models.<n> COLA restores global image-text alignment and local structural consistency in the feature space.<n> COLA is training-free and compatible with existing fine-tuned models.
  arXiv  Detail & Related papers  (2025-10-28T03:47:44Z)
• Taming the Tri-Space Tension: ARC-Guided Hallucination Modeling and Control for Text-to-Image Generation [1.668665305941319]
  Text-to-image (T2I) diffusion models exhibit persistent "hallucinations"<n>We propose a cognitively inspired perspective that reinterprets hallucinations as trajectory drift within a latent alignment space.<n>This framework offers a unified and interpretable approach for understanding and mitigating generative failures in T2I systems.
  arXiv  Detail & Related papers  (2025-07-07T12:43:09Z)
• Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection [50.343419243749054]
  Anomaly detection is critical in fields such as medical diagnostics and industrial defect detection.<n> CLIP's coarse-grained image-text alignment limits localization and detection performance for fine-grained anomalies.<n>Crane improves the state-of-the-art ZSAD from 2% to 28%, at both image and pixel levels, while remaining competitive in inference speed.
  arXiv  Detail & Related papers  (2025-04-15T10:42:25Z)
• VICCA: Visual Interpretation and Comprehension of Chest X-ray Anomalies in Generated Report Without Human Feedback [1.5839621757142595]
  We propose a novel framework designed to enhance the semantic alignment and localization accuracy of AI-generated medical reports.<n>By comparing features between the original and generated images, we introduce a dual-scoring system.<n>This approach significantly outperforms existing methods, achieving state-of-the-art results in pathology localization and text-to-image alignment.
  arXiv  Detail & Related papers  (2025-01-29T16:02:16Z)
• Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection [106.39544368711427]
  We study the problem of generalizable synthetic image detection, aiming to detect forgery images from diverse generative methods. We present a novel forgery-aware adaptive transformer approach, namely FatFormer. Our approach tuned on 4-class ProGAN data attains an average of 98% accuracy to unseen GANs, and surprisingly generalizes to unseen diffusion models with 95% accuracy.
  arXiv  Detail & Related papers  (2023-12-27T17:36:32Z)
• Transferable Class-Modelling for Decentralized Source Attribution of GAN-Generated Images [4.1483423188102755]
  We redefine the deepfake detection and source attribution problems as a series of related binary classification tasks. We leverage transfer learning to rapidly adapt forgery detection networks for multiple independent attribution problems. Our models are determined via experimentation to be competitive with current benchmarks.
  arXiv  Detail & Related papers  (2022-03-18T07:43:03Z)

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.