DWA: Differential Wavelet Amplifier for Image Super-Resolution
Not on the map. Why?
Abstract (arXiv)
This work introduces Differential Wavelet Amplifier (DWA), a drop-in module for wavelet-based image Super-Resolution (SR). DWA invigorates an approach recently receiving less attention, namely Discrete Wavelet Transformation (DWT). DWT enables an efficient image representation for SR and reduces the spatial area of its input by a factor of 4, the overall model size, and computation cost, framing it as an attractive approach for sustainable ML. Our proposed DWA model improves wavelet-based SR models by leveraging the difference between two convolutional filters to refine relevant feature extraction in the wavelet domain, emphasizing local contrasts and suppressing common noise in the input signals. We show its effectiveness by integrating it into existing SR models, e.g., DWSR and MWCNN, and demonstrate a clear improvement in classical SR tasks. Moreover, DWA enables a direct application of DWSR and MWCNN to input image space, reducing the DWT representation channel-wise since it omits traditional DWT.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 32 references that are in the map. First posted on arXiv 10 Jul 2023.
Builds on
16 of 32 references.
References · 16
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
- 2021Image Super-Resolution via Iterative Refinementcited by 1,506
- 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
- 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
- 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
- 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
- 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
- 2019Deep Learning for Image Super-resolution: A Surveycited by 368
4 more
- 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
- 2023Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolutioncited by 56
- 2023Denoising Diffusion Probabilistic Models for Robust Image Super-Resolution in the Wildcited by 46
- 2022Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advancescited by 21
Built on by
Citing papers per year: 2023: 1; 2024: 3.
4 papers.
- 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
- 2023Dynamic Attention-Guided Diffusion for Image Super-Resolutioncited by 10
- 2024A Wavelet Diffusion GAN for Image Super-Resolutioncited by 4
- 2024A Low-Resolution Image is Worth 1x1 Words: Enabling Fine Image Super-Resolution with Transformers and TaylorShiftcited by 1
- 2024A Low-Resolution Image is Worth 1x1 Words: Enabling Fine Image Super-Resolution with Transformers and TaylorShift15 Nov 2024
- 2024A Wavelet Diffusion GAN for Image Super-Resolution23 Oct 2024
- 2024Diffusion Models, Image Super-Resolution And Everything: A Survey1 Jan 2024
- 2023Dynamic Attention-Guided Diffusion for Image Super-Resolution15 Aug 2023