mlsanityData to 7 Oct 2026

Improved Image Generation via Sparse Modeling

arXiv 2104.00464 ↗First posted 1 Apr 2021cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

The interest of the deep learning community in image synthesis has grown massively in recent years. Nowadays, deep generative methods, and especially Generative Adversarial Networks (GANs), are leading to state-of-the-art performance, capable of synthesizing images that appear realistic. While the efforts for improving the quality of the generated images are extensive, most attempts still consider the generator part as an uncorroborated "black-box". In this paper, we aim to provide a better understanding and design of the image generation process. We interpret existing generators as implicitly relying on sparsity-inspired models. More specifically, we show that generators can be viewed as manifestations of the Convolutional Sparse Coding (CSC) and its Multi-Layered version (ML-CSC) synthesis processes. We leverage this observation by explicitly enforcing a sparsifying regularization on appropriately chosen activation layers in the generator, and demonstrate that this leads to improved image synthesis. Furthermore, we show that the same rationale and benefits apply to generators serving inverse problems, demonstrated on the Deep Image Prior (DIP) method.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 45 references that are in the map. First posted on arXiv 1 Apr 2021.

Builds on

24 of 45 references.

References · 24

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  4. 2016Improved Techniques for Training GANscited by 2,938
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2017Improved Training of Wasserstein GANscited by 2,223
  7. 2014Conditional Generative Adversarial Netscited by 2,152
  8. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  9. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  10. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  11. 2017Deep Image Priorcited by 1,097
  12. 2016Least Squares Generative Adversarial Networkscited by 1,000
12 more
  1. 2018Self-Attention Generative Adversarial Networkscited by 809
  2. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  3. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  4. 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
  5. 2016Convolutional Neural Networks Analyzed via Convolutional Sparse Codingcited by 51
  6. 2014Sparse Modeling for Image and Vision Processingcited by 48
  7. 2019Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Gamecited by 25
  8. 2019Rethinking the CSC Model for Natural Imagescited by 21
  9. 2017Convolutional Dictionary Learning via Local Processingcited by 19
  10. 2017Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learningcited by 14
  11. 2019Sparse Generative Adversarial Networkcited by 8
  12. 2018A Greedy Approach to ℓ0,∞ Based Convolutional Sparse Codingcited by 2

Built on by

Not cited yet.