Saved in:
Bibliographic Details
Main Authors: Yang, Chao, Fan, Yong, Zhang, Qichao, Lu, Cheng, Yang, Zhijing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.12567
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916845847576576
author Yang, Chao
Fan, Yong
Zhang, Qichao
Lu, Cheng
Yang, Zhijing
author_facet Yang, Chao
Fan, Yong
Zhang, Qichao
Lu, Cheng
Yang, Zhijing
contents Recently, the transfer application of diffusion models in super-resolu-tion tasks has faced the problem ofdecreased fidelity. Due to the inherent randomsampling characteristics ofdiffusion models, direct application in super-resolu-tion tasks can result in generated details deviating from the true distribution ofhigh-resolution images. To address this, we propose DeltaDiff, a novel frame.work that constrains the difusion process, its essence is to establish a determin-istic mapping path between HR and LR, rather than the random noise disturbanceprocess oftraditional difusion models. Theoretical analysis demonstrates a 25%reduction in diffusion entropy in the residual space compared to pixel-space diffiusion, effectively suppressing irrelevant noise interference. The experimentalresults show that our method surpasses state-of-the-art models and generates re-sults with better fidelity. This work establishes a new low-rank constrained par-adigm for applying diffusion models to image reconstruction tasks, balancingstochastic generation with structural fidelity. Our code and model are publiclyavailable at https://github.com/continueyang/DeltaDiff .
format Preprint
id arxiv_https___arxiv_org_abs_2502_12567
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeltaDiff: Reality-Driven Diffusion with AnchorResiduals for Faithful SR
Yang, Chao
Fan, Yong
Zhang, Qichao
Lu, Cheng
Yang, Zhijing
Computer Vision and Pattern Recognition
Recently, the transfer application of diffusion models in super-resolu-tion tasks has faced the problem ofdecreased fidelity. Due to the inherent randomsampling characteristics ofdiffusion models, direct application in super-resolu-tion tasks can result in generated details deviating from the true distribution ofhigh-resolution images. To address this, we propose DeltaDiff, a novel frame.work that constrains the difusion process, its essence is to establish a determin-istic mapping path between HR and LR, rather than the random noise disturbanceprocess oftraditional difusion models. Theoretical analysis demonstrates a 25%reduction in diffusion entropy in the residual space compared to pixel-space diffiusion, effectively suppressing irrelevant noise interference. The experimentalresults show that our method surpasses state-of-the-art models and generates re-sults with better fidelity. This work establishes a new low-rank constrained par-adigm for applying diffusion models to image reconstruction tasks, balancingstochastic generation with structural fidelity. Our code and model are publiclyavailable at https://github.com/continueyang/DeltaDiff .
title DeltaDiff: Reality-Driven Diffusion with AnchorResiduals for Faithful SR
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.12567