Heterogeneous window transformer for image denoising
Deep networks can usually depend on extracting more structural information to improve denoising results. However, they may ignore correlation between pixels from an image to pursue better denoising performance. Window transformer can use long- and short-distance modeling to interact pixels to address mentioned problem. To make a tradeoff between distance modeling and denoising time, we propose a heterogeneous window transformer (HWformer) for image denoising. HWformer first designs heterogeneous global windows to capture global context information for improving denoising effects. To build a bridge between long and short-distance modeling, global windows are horizontally and vertically shifted to facilitate diversified information without increasing denoising time. To prevent the information loss phenomenon of independent patches, sparse idea is guided a feed-forward network to extract local information of neighboring patches. The proposed HWformer only takes 30% of popular Restormer in terms of denoising time.
Code (1)
Tasks
DenoisingImage DenoisingSimilar Papers 제목 키워드 기반
CUR Transformer: A Convolutional Unbiased Regional Transformer for Image Denoising
Image denoising is a fundamental problem in computer vision and multimedia computation. Non-local filters are effective for image denoising. But existing deep learning methods that use non-local computation structures ar…
DenoisingImage DenoisingImage EnhancementJpeg Compression Artifact Reduction+1Eformer: Edge Enhancement based Transformer for Medical Image Denoising
In this work, we present Eformer - Edge enhancement based transformer, a novel architecture that builds an encoder-decoder network using transformer blocks for medical image denoising. Non-overlapping window-based self-a…
DecoderDenoisingImage DenoisingMedical Image Denoising+1HAT: Hybrid Attention Transformer for Image Restoration
Transformer-based methods have shown impressive performance in image restoration tasks, such as image super-resolution and denoising. However, we find that these networks can only utilize a limited spatial range of input…
DenoisingImage CompressionImage DenoisingImage Restoration+2Spatial-Frequency Attention for Image Denoising
The recently developed transformer networks have achieved impressive performance in image denoising by exploiting the self-attention (SA) in images. However, the existing methods mostly use a relatively small window to c…
DenoisingImage DenoisingLightweight Video Denoising Using a Classic Bayesian Backbone
In recent years, state-of-the-art image and video denoising networks have become increasingly large, requiring millions of trainable parameters to achieve best-in-class performance. Improved denoising quality has come at…
DenoisingVideo Denoising