Refining Visual Artifacts in Diffusion Models via Explainable AI-based Flaw Activation Maps

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Seoyeon, Yu, Gwangyeol, Kim, Chaewon, Park, Jonghyuk
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912755714359296
author Lee, Seoyeon
Yu, Gwangyeol
Kim, Chaewon
Park, Jonghyuk
author_facet Lee, Seoyeon
Yu, Gwangyeol
Kim, Chaewon
Park, Jonghyuk
contents Diffusion models have achieved remarkable success in image synthesis. However, addressing artifacts and unrealistic regions remains a critical challenge. We propose self-refining diffusion, a novel framework that enhances image generation quality by detecting these flaws. The framework employs an explainable artificial intelligence (XAI)-based flaw highlighter to produce flaw activation maps (FAMs) that identify artifacts and unrealistic regions. These FAMs improve reconstruction quality by amplifying noise in flawed regions during the forward process and by focusing on these regions during the reverse process. The proposed approach achieves up to a 27.3% improvement in Fréchet inception distance across various diffusion-based models, demonstrating consistently strong performance on diverse datasets. It also shows robust effectiveness across different tasks, including image generation, text-to-image generation, and inpainting. These results demonstrate that explainable AI techniques can extend beyond interpretability to actively contribute to image refinement. The proposed framework offers a versatile and effective approach applicable to various diffusion models and tasks, significantly advancing the field of image synthesis.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08774
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Refining Visual Artifacts in Diffusion Models via Explainable AI-based Flaw Activation Maps
Lee, Seoyeon
Yu, Gwangyeol
Kim, Chaewon
Park, Jonghyuk
Computer Vision and Pattern Recognition
Artificial Intelligence
Diffusion models have achieved remarkable success in image synthesis. However, addressing artifacts and unrealistic regions remains a critical challenge. We propose self-refining diffusion, a novel framework that enhances image generation quality by detecting these flaws. The framework employs an explainable artificial intelligence (XAI)-based flaw highlighter to produce flaw activation maps (FAMs) that identify artifacts and unrealistic regions. These FAMs improve reconstruction quality by amplifying noise in flawed regions during the forward process and by focusing on these regions during the reverse process. The proposed approach achieves up to a 27.3% improvement in Fréchet inception distance across various diffusion-based models, demonstrating consistently strong performance on diverse datasets. It also shows robust effectiveness across different tasks, including image generation, text-to-image generation, and inpainting. These results demonstrate that explainable AI techniques can extend beyond interpretability to actively contribute to image refinement. The proposed framework offers a versatile and effective approach applicable to various diffusion models and tasks, significantly advancing the field of image synthesis.
title Refining Visual Artifacts in Diffusion Models via Explainable AI-based Flaw Activation Maps
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.08774