提出无混叠的UNet，提升图像修复的平移等变性。
UNet-AF: An alias-free UNet for image restoration
- 采用前沿等变层构建新UNet，避免传统层的混叠问题。
- 在图像修复任务中表现媲美基线，等变性显著增强。
- 适合关注模型几何不变性的图像处理研究者。
UNet结构因简洁高效被广泛用于图像修复、分割及扩散模型。尽管常假设其具备平移等变性，但传统网络层易产生混叠，实际削弱了等变性。为此，我们提出一种全新无混叠UNet，基于对先进平移等变层的精心选择。在图像修复任务上，该等变架构与非等变基线对比，性能相当且等变性明显提升。通过大量消融实验，验证每项设计对实证等变性的关键作用。代码已公开于 https://github.com/jscanvic/UNet-AF。
原文摘要 · Abstract (English)
The simplicity and effectiveness of the UNet architecture makes it ubiquitous in image restoration, image segmentation, and diffusion models. They are often assumed to be equivariant to translations, yet they traditionally consist of layers that are known to be prone to aliasing, which hinders their equivariance in practice. To overcome this limitation, we propose a new alias-free UNet designed from a careful selection of state-of-the-art translation-equivariant layers. We evaluate the proposed equivariant architecture against non-equivariant baselines on image restoration tasks and observe competitive performance with a significant increase in measured equivariance. Through extensive ablation studies, we also demonstrate that each change is crucial for its empirical equivariance. Our implementation is available at https://github.com/jscanvic/UNet-AF
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。