发表机构
Mahindra University（马恒达大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Hybrid++提出一种可训练的非线性反应扩散架构，结合PDE可解释性与深度学习性能，在伽马噪声去除中接近DnCNN效果且参数极少。
AI 中文摘要
乘性伽马噪声是合成孔径雷达（SAR）和医学超声图像中的主要噪声因素之一。由于它们依赖于像素级噪声，因此在图像中变化很大，与加性噪声相比更难处理。目前解决此噪声的去噪方法包括经典的偏微分方程（PDE）方法，这些方法具有良好的可解释性，但与最先进的模型相比缺乏恢复能力，而深度卷积网络如DnCNN虽然实现了高性能，但以透明度为代价，导致从业者对其在高风险关键领域（如医学）中的使用持怀疑态度。本文提出了Hybrid++，一种新颖的可训练非线性反应扩散架构，它同时解决了这两个问题——保持可解释性，同时提供接近大型黑盒模型的性能。它结合了完全可学习的PDE初始化与一个3阶段反应扩散网络，该网络具有64通道多尺度滤波器组、4层基于Squeeze-and-Excitation注意力的影响函数和64维噪声水平嵌入。它采用两阶段训练策略，即阶段式优化后接联合端到端细化，这使得所有可学习参数能够共同适应。在FoE基准上，Hybrid++显著优于经典PDE、BM3D和原始TNRD基线。在严重噪声设置L=1下，其PSNR比单独训练的DnCNN低0.23 dB，而仅使用其约8%的参数。因此，我们将Hybrid++定位为一种紧凑的、物理结构的反应扩散模型，用于乘性伽马噪声，而非通用的最先进图像恢复骨干网络。
英文摘要
Multiplicative gamma noise is one of the dominant noise factors in Synthetic Aperture Radar (SAR) and medical ultrasound images. They are dependent on pixel level noises due to which they are highly varying across the image and harder to handle as compared to additive noise. The denoising methods to address this noise currently include classical partial differential equation (PDE) methods which are good for interpretation but lack the restoration ability as compared to the state-of-the-art models while deep convolutional networks like DnCNN achieve high performance but at the cost of transparency due to which practitioners are skeptical to use them in high-risk critical fields like medicine. This paper presents Hybrid++, a novel trainable nonlinear reaction-diffusion architecture that addresses both the concerns - staying interpretable while offering performance close to huge black-box models. It combines a fully learnable PDE initialization with a 3-stage reaction-diffusion network having 64-channel multiscale filter banks, 4-layer Squeeze-and-Excitation attention-based influence functions and a 64-dimensional noise level embedding. It uses a two-phase training strategy, stage-wise optimization followed by joint end-to-end refinement which enables co-adaptation of all learnable parameters. On the FoE benchmark, Hybrid++ substantially improves over classical PDE, BM3D and the original TNRD baselines. In the severe-noise setting L=1, it comes within 0.23 dB PSNR of a separately trained DnCNN while using only about 8% of its parameters. We therefore position Hybrid++ not as a universal state-of-the-art image restoration backbone, but as a compact, physically structured reaction-diffusion model for multiplicative gamma noise.
