提出新方法，让去噪同时保留细节，突破现有技术瓶颈。
Next-Scale Prediction: A Self-Supervised Approach for Real-World Image Denoising
- 用跨尺度预测解耦降噪与细节保持
- 在Real-World数据集上达当前最优效果
- 可直接用于噪声图像超分，无需额外训练
自监督真实世界图像去噪仍面临核心挑战：如何在消除空间结构化噪声的同时保留高频细节。现有盲区网络（BSN）依赖像素洗牌下采样（PD）实现噪声解相关，但过度下采样会破坏精细结构，而轻度下采样又无法有效去除相关噪声。为此，本文提出一种新范式——跨尺度预测（NSP），将噪声解相关与细节保留分离处理。NSP构建跨尺度训练对，使BSN以低分辨率、完全解相关的子图为输入，预测保留细粒度特征的高分辨率目标。作为副产品，该方法无需重新训练即可支持噪声图像的超分辨率。大量实验表明，NSP在真实世界基准上达到自监督去噪的最先进性能，显著缓解了噪声解相关与细节保留之间的长期矛盾。代码已公开于 https://github.com/XLearning-SCU/2026-CVPR-NSP。
原文摘要 · Abstract (English)
Self-supervised real-world image denoising remains a fundamental challenge, arising from the antagonistic trade-off between decorrelating spatially structured noise and preserving high-frequency details. Existing blind-spot network (BSN) methods rely on pixel-shuffle downsampling (PD) to decorrelate noise, but aggressive downsampling fragments fine structures, while milder downsampling fails to remove correlated noise. To address this, we introduce Next-Scale Prediction (NSP), a novel self-supervised paradigm that decouples noise decorrelation from detail preservation. NSP constructs cross-scale training pairs, where BSN takes low-resolution, fully decorrelated sub-images as input to predict high-resolution targets that retain fine details. As a by-product, NSP naturally supports super-resolution of noisy images without retraining or modification. Extensive experiments demonstrate that NSP achieves state-of-the-art self-supervised denoising performance on real-world benchmarks, significantly alleviating the long-standing conflict between noise decorrelation and detail preservation. The code is available at https://github.com/XLearning-SCU/2026-CVPR-NSP.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。