Thunder: Thumbnail based Fast Lightweight Image Denoising Network
Not on the map. Why?
Abstract (arXiv)
To achieve promising results on removing noise from real-world images, most of existing denoising networks are formulated with complex network structure, making them impractical for deployment. Some attempts focused on reducing the number of filters and feature channels but suffered from large performance loss, and a more practical and lightweight denoising network with fast inference speed is of high demand. To this end, a Thumbnail based Denoising Network dubbed Thunder, is proposed and implemented as a lightweight structure for fast restoration without comprising the denoising capabilities. Specifically, the Thunder model contains two newly-established modules: (1) a wavelet-based Thumbnail Subspace Encoder (TSE) which can leverage sub-bands correlation to provide an approximate thumbnail based on the low-frequent feature; (2) a Subspace Projection based Refine Module (SPR) which can restore the details for thumbnail progressively based on the subspace projection approach. Extensive experiments have been carried out on two real-world denoising benchmarks, demonstrating that the proposed Thunder outperforms the existing lightweight models and achieves competitive performance on PSNR and SSIM when compared with the complex designs.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 24 May 2022.
Builds on
23 of 33 references.
References · 23
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
- 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 510
- 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
- 2017Benchmarking Denoising Algorithms with Real Photographscited by 209
- 2019Deep Stacked Hierarchical Multi-patch Network for Image Deblurringcited by 206
- 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
- 2019Real Image Denoising with Feature Attentioncited by 176
- 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
- 2020Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurringcited by 119
- 2019Variational Denoising Network: Toward Blind Noise Modeling and Removalcited by 117
- 2020Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generationcited by 101
11 more
- 2020Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalizationcited by 92
- 2020NBNet: Noise Basis Learning for Image Denoising with Subspace Projectioncited by 77
- 2020Practical Deep Raw Image Denoising on Mobile Devicescited by 76
- 2021Invertible Denoising Network: A Light Solution for Real Noise Removalcited by 68
- 2022C2N: Practical Generative Noise Modeling for Real-World Denoisingcited by 56
- 2019When AWGN-based Denoiser Meets Real Noisescited by 53
- 2021Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolutioncited by 52
- 2020MPRNet: Multi-Path Residual Network for Lightweight Image Super Resolutioncited by 38
- 2018Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolutioncited by 24
- 2016Generalized Deep Image to Image Regressioncited by 14
- 2021Deep Universal Blind Image Denoisingcited by 10
Built on by
Citing papers per year: 2023: 2.
2 papers.