Stop Denoising Your Blurs 事件

Stop Denoising Your Blurs 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 nov