Consistent Diffusion: Denoising Diffusion Model with Data-Consistent Training for Image Restoration

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cheng, Xinlong, Cao, Tiantian, Cheng, Guoan, Huang, Bangxuan, Tian, Xinghan, Wang, Ye, He, Xiaoyu, Li, Weixin, Xue, Tianfan, Dong, Xuan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929635022864384
author Cheng, Xinlong
Cao, Tiantian
Cheng, Guoan
Huang, Bangxuan
Tian, Xinghan
Wang, Ye
He, Xiaoyu
Li, Weixin
Xue, Tianfan
Dong, Xuan
author_facet Cheng, Xinlong
Cao, Tiantian
Cheng, Guoan
Huang, Bangxuan
Tian, Xinghan
Wang, Ye
He, Xiaoyu
Li, Weixin
Xue, Tianfan
Dong, Xuan
contents In this work, we address the limitations of denoising diffusion models (DDMs) in image restoration tasks, particularly the shape and color distortions that can compromise image quality. While DDMs have demonstrated a promising performance in many applications such as text-to-image synthesis, their effectiveness in image restoration is often hindered by shape and color distortions. We observe that these issues arise from inconsistencies between the training and testing data used by DDMs. Based on our observation, we propose a novel training method, named data-consistent training, which allows the DDMs to access images with accumulated errors during training, thereby ensuring the model to learn to correct these errors. Experimental results show that, across five image restoration tasks, our method has significant improvements over state-of-the-art methods while effectively minimizing distortions and preserving image fidelity.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12550
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Consistent Diffusion: Denoising Diffusion Model with Data-Consistent Training for Image Restoration
Cheng, Xinlong
Cao, Tiantian
Cheng, Guoan
Huang, Bangxuan
Tian, Xinghan
Wang, Ye
He, Xiaoyu
Li, Weixin
Xue, Tianfan
Dong, Xuan
Computer Vision and Pattern Recognition
In this work, we address the limitations of denoising diffusion models (DDMs) in image restoration tasks, particularly the shape and color distortions that can compromise image quality. While DDMs have demonstrated a promising performance in many applications such as text-to-image synthesis, their effectiveness in image restoration is often hindered by shape and color distortions. We observe that these issues arise from inconsistencies between the training and testing data used by DDMs. Based on our observation, we propose a novel training method, named data-consistent training, which allows the DDMs to access images with accumulated errors during training, thereby ensuring the model to learn to correct these errors. Experimental results show that, across five image restoration tasks, our method has significant improvements over state-of-the-art methods while effectively minimizing distortions and preserving image fidelity.
title Consistent Diffusion: Denoising Diffusion Model with Data-Consistent Training for Image Restoration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.12550