mlsanityData to 7 Oct 2026

Neural Sparse Representation for Image Restoration

arXiv 2006.04357 ↗First posted 8 Jun 2020cs.CVcited by 22

Not on the map. Why?

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

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 4; 2023: 3; 2024: 5; 2025: 6; 2026: 2.

22 papers.

Sort:

By area:

  1. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  2. 2022Revisiting RCAN: Improved Training for Image Super-Resolutioncited by 32
  3. 2022Deep Fourier Up-Samplingcited by 27
  4. 2025Dual Prompting Image Restoration with Diffusion Transformerscited by 15
  5. 2022HIPA: Hierarchical Patch Transformer for Single Image Super Resolutioncited by 11
  6. 2023High-Similarity-Pass Attention for Single Image Super-Resolutioncited by 11
  7. 2025Frequency Domain-Based Diffusion Model for Unpaired Image Dehazingcited by 11
  8. 2021Unfolding Taylor's Approximations for Image Restorationcited by 6
  9. 2024Dynamic Contrastive Knowledge Distillation for Efficient Image Restorationcited by 6
  10. 2025Learning without Isolation: Pathway Protection for Continual Learningcited by 6
  11. 2022Visual Attention Emerges from Recurrent Sparse Reconstructioncited by 3
  12. 2023GRAN: Ghost Residual Attention Network for Single Image Super Resolutioncited by 3
10 more
  1. 2025Plug-and-Play Image Restoration with Flow Matching: A Continuous Viewpointcited by 3
  2. 2024Block Sparse Bayesian Learning: A Diversified Schemecited by 2
  3. 2025Learning Deblurring Texture Prior from Unpaired Data with Diffusion Modelcited by 2
  4. 2025RDDM: Practicing RAW Domain Diffusion Model for Real-world Image Restorationcited by 2
  5. 2021RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Networkcited by 1
  6. 2023Random Weights Networks Work as Loss Prior Constraint for Image Restorationcited by 0
  7. 2024Look-Around Before You Leap: High-Frequency Injected Transformer for Image Restorationcited by 0
  8. 2024Efficient Image Restoration through Low-Rank Adaptation and Stable Diffusion XLcited by 0
  9. 2026A Cosine Network for Image Super-Resolutioncited by 0
  10. 2026MagnifiQ: Patch-aware Text Guided Progressive Upscaling for High-Resolution Image Restorationcited by 0