发表机构
Tsinghua University; The Chinese University of Hong Kong; University of Southern California; Peking University（清华大学; 香港中文大学; 南加州大学; 北京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对单图像自监督去噪问题，提出LoTA-N2N两阶段零样本自适应框架，通过估计局部相互作用和控制空间抵消，在多种噪声下实验效果优于仅基于MSE的方法，为无配对干净目标等情况的自监督去噪提供有效设计原则。
AI 中文摘要
单图像自监督去噪使用从噪声观测构建的替代目标来替换不可用的干净目标。其有效性取决于替代目标与监督去噪的对齐程度，特别是在噪声相关、空间非平稳或未知时。我们将基于MSE的自监督目标与监督MSE之间的差异表示为与参数无关的常数以及替代目标残差与预测误差之间的迹线相互作用。相应的梯度差异由这种相互作用的梯度决定。在此基础上，我们提出了LoTA-N2N，一个两阶段的零样本自适应框架。第一阶段在互补子图像对上训练去噪器并冻结它以构建分离的干净子图像代理。第二阶段使用这些代理估计残差-预测相互作用并抑制其逐块绝对值。实验表明LoTA-N2N在多种噪声情况下优于仅基于MSE的自适应方法，证明了估计局部相互作用和空间抵消控制为单图像自监督去噪提供了有效的设计原则。
英文摘要
Single-image self-supervised denoising replaces unavailable clean targets with surrogate targets constructed from noisy observations. Its effectiveness therefore depends on how closely the surrogate objective remains aligned with supervised denoising, especially when noise is correlated, spatially nonstationary, or unknown. We express the discrepancy between a broad class of MSE-based self-supervised objectives and supervised MSE as a parameter-independent constant and a trace interaction between the surrogate-target residual and the prediction error. The corresponding gradient discrepancy is determined by the gradient of this interaction. This formulation provides a common view of paired-noise, blind-spot, weak-noise, re-corruption, and sub-image methods, while revealing that a small global interaction may conceal substantial positive and negative regional interactions through spatial cancellation. Building on these observations, we propose LoTA-N2N, a two-stage zero-shot adaptation framework. Stage 1 trains a denoiser on complementary sub-image pairs and freezes it to construct detached clean-sub-image proxies. Stage 2 estimates the residual--prediction interaction using these proxies and suppresses its patch-wise absolute magnitude. We show that the local construction prevents spatial cancellation and upper-bounds the magnitude of the corresponding global interaction. Experiments across natural, confocal, and X-ray images, complemented by iteration-matched controls, controlled noise shifts, and gradient diagnostics, show consistent gains over MSE-only adaptation under IID, spatially varying, and mixed noise. Overall, LoTA-N2N demonstrates that estimated local interaction and spatial cancellation control provide effective design principles for single-image self-supervised denoising without paired clean targets, repeated acquisitions, or a predefined re-corruption model.
Comments22pages, 9 tables, 11 figures
