# Neural Sparse Representation for Image Restoration

arXiv: https://arxiv.org/abs/2006.04357 · HTML: https://mlsanity.com/paper/2006.04357/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2020.

## Built on by (most cited first, 22 of 22)

- [Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild](https://mlsanity.com/paper/2401.13627/) (2024)
- [Revisiting RCAN: Improved Training for Image Super-Resolution](https://mlsanity.com/paper/2201.11279/) (2022)
- [Deep Fourier Up-Sampling](https://mlsanity.com/paper/2210.05171/) (2022)
- [Dual Prompting Image Restoration with Diffusion Transformers](https://mlsanity.com/paper/2504.17825/) (2025)
- [HIPA: Hierarchical Patch Transformer for Single Image Super Resolution](https://mlsanity.com/paper/2203.10247/) (2022)
- [High-Similarity-Pass Attention for Single Image Super-Resolution](https://mlsanity.com/paper/2305.15768/) (2023)
- [Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing](https://mlsanity.com/paper/2507.01275/) (2025)
- [Unfolding Taylor's Approximations for Image Restoration](https://mlsanity.com/paper/2109.03442/) (2021)
- [Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration](https://mlsanity.com/paper/2412.08939/) (2024)
- [Learning without Isolation: Pathway Protection for Continual Learning](https://mlsanity.com/paper/2505.18568/) (2025)
- [Visual Attention Emerges from Recurrent Sparse Reconstruction](https://mlsanity.com/paper/2204.10962/) (2022)
- [GRAN: Ghost Residual Attention Network for Single Image Super Resolution](https://mlsanity.com/paper/2302.14557/) (2023)
- [Plug-and-Play Image Restoration with Flow Matching: A Continuous Viewpoint](https://mlsanity.com/paper/2512.04283/) (2025)
- [Block Sparse Bayesian Learning: A Diversified Scheme](https://mlsanity.com/paper/2402.04646/) (2024)
- [Learning Deblurring Texture Prior from Unpaired Data with Diffusion Model](https://mlsanity.com/paper/2507.13599/) (2025)
- [RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restoration](https://mlsanity.com/paper/2508.19154/) (2025)
- [RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network](https://mlsanity.com/paper/2110.13217/) (2021)
- [Random Weights Networks Work as Loss Prior Constraint for Image Restoration](https://mlsanity.com/paper/2303.16438/) (2023)
- [Look-Around Before You Leap: High-Frequency Injected Transformer for Image Restoration](https://mlsanity.com/paper/2404.00279/) (2024)
- [Efficient Image Restoration through Low-Rank Adaptation and Stable Diffusion XL](https://mlsanity.com/paper/2408.17060/) (2024)
- [A Cosine Network for Image Super-Resolution](https://mlsanity.com/paper/2601.16413/) (2026)
- [MagnifiQ: Patch-aware Text Guided Progressive Upscaling for High-Resolution Image Restoration](https://mlsanity.com/paper/2608.14543/) (2026)

## Abstract (arXiv)

Inspired by the robustness and efficiency of sparse representation in sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks. Our method structurally enforces sparsity constraints upon hidden neurons. The sparsity constraints are favorable for gradient-based learning algorithms and attachable to convolution layers in various networks. Sparsity in neurons enables computation saving by only operating on non-zero components without hurting accuracy. Meanwhile, our method can magnify representation dimensionality and model capacity with negligible additional computation cost. Experiments show that sparse representation is crucial in deep neural networks for multiple image restoration tasks, including image super-resolution, image denoising, and image compression artifacts removal. Code is available at https://github.com/ychfan/nsr