Stop Denoising Your Blurs 文章

ArXiv CS.CV2026-05-26NEWSen作者: Sasidhar Parvathireddy, Vamsidhar Saraswathula, Rama Krishna Gorthi

摘要

arXiv:2605.25014v1 Announce Type: new Abstract: In recent times, diffusion models have achieved remarkable performance in image restoration tasks. Their core mechanism relies on the restricted presumption of degradation prior to the additive noise operation. However, the blur model, one of the most widely studied degradation formulations, violates this assumption, as it is inherently based on convolution rather than addition. In this paper, we introduce ConvDiff, a novel diffusion based framework that substitutes the additive operation with convolution for the task of image deblurring. In the forward process, we construct a meaningful trajectory from the clean image to its blurred counterpart by exploiting the frequency domain characteristics of convolution, rather than progressively corrupting the image with additive noise.

相关事件查看全部 (1)

Stop Denoising Your Blurs
2026-05-26PRODUCT_LAUNCH影响: MEDIUM

相关公司

暂无数据

相关人物

暂无数据