IRNeXt: Rethinking Convolutional Network Design for Image Restoration
We present IRNeXt, a simple yet effective convolutional network architecture for image restoration. Recently, Transformer models have dominated the field of image restoration due to the powerful ability of modeling long-range pixels interactions. In this paper, we excavate the potential of the convolutional neural network (CNN) and show that our CNN-based model can receive comparable or better performance than Transformer models with low computation overhead on several image restoration tasks. By re-examining the characteristics possessed by advanced image restoration algorithms, we discover several key factors leading to the performance improvement of restoration models. This motivates us to develop a novel network for image restoration based on cheap convolution operators. Comprehensive experiments demonstrate that IRNeXt delivers state-of-the-art performance among numerous datasets on a range of image restoration tasks with low computational complexity, including image dehazing, single-image defocus/motion deblurring, image deraining, and image desnowing.
PDF
GoPro
RESIDE
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Image Deblurring | GoPro | IRNeXt | PSNR | 33.16 | # 16 | |
| SSIM | 0.962 | # 17 | ||||
| Image Dehazing | SOTS Indoor | IRNeXt | PSNR | 41.21 | # 9 | |
| SSIM | 0.996 | # 5 | ||||
| Image Dehazing | SOTS Outdoor | IRNeXt | PSNR | 39.18 | # 4 | |
| SSIM | 0.996 | # 3 |
