SwinIA: Self-Supervised Blind-Spot Image Denoising without Convolutions
This addresses the problem of efficient and flexible denoising for image processing applications, representing a novel architectural shift rather than an incremental improvement.
The paper tackled self-supervised image denoising without ground truth by proposing SwinIA, a fully-transformer architecture that eliminates the need for multiple forward passes or noise model knowledge, establishing state-of-the-art results on several benchmarks.
Self-supervised image denoising implies restoring the signal from a noisy image without access to the ground truth. State-of-the-art solutions for this task rely on predicting masked pixels with a fully-convolutional neural network. This most often requires multiple forward passes, information about the noise model, or intricate regularization functions. In this paper, we propose a Swin Transformer-based Image Autoencoder (SwinIA), the first fully-transformer architecture for self-supervised denoising. The flexibility of the attention mechanism helps to fulfill the blind-spot property that convolutional counterparts normally approximate. SwinIA can be trained end-to-end with a simple mean squared error loss without masking and does not require any prior knowledge about clean data or noise distribution. Simple to use, SwinIA establishes the state of the art on several common benchmarks.