mlsanityData to 7 Oct 2026

VSpSR: Explorable Super-Resolution via Variational Sparse Representation

arXiv 2104.08575 ↗First posted 17 Apr 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Super-resolution (SR) is an ill-posed problem, which means that infinitely many high-resolution (HR) images can be degraded to the same low-resolution (LR) image. To study the one-to-many stochastic SR mapping, we implicitly represent the non-local self-similarity of natural images and develop a Variational Sparse framework for Super-Resolution (VSpSR) via neural networks. Since every small patch of a HR image can be well approximated by the sparse representation of atoms in an over-complete dictionary, we design a two-branch module, i.e., VSpM, to explore the SR space. Concretely, one branch of VSpM extracts patch-level basis from the LR input, and the other branch infers pixel-wise variational distributions with respect to the sparse coefficients. By repeatedly sampling coefficients, we could obtain infinite sparse representations, and thus generate diverse HR images. According to the preliminary results of NTIRE 2021 challenge on learning SR space, our team (FudanZmic21) ranks 7-th in terms of released scores. The implementation of VSpSR is released at https://zmiclab.github.io/.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 17 Apr 2021.

Builds on

20 of 32 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  4. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  5. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  6. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  7. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  8. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  9. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  10. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  11. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
  12. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
8 more
  1. 2018Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Networkcited by 263
  2. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  3. 2019Meta-SR: A Magnification-Arbitrary Network for Super-Resolutioncited by 180
  4. 2016Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensationcited by 156
  5. 2018Wide Activation for Efficient and Accurate Image Super-Resolutioncited by 64
  6. 2019Explorable Super Resolutioncited by 44
  7. 2020DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-Resolutioncited by 17
  8. 2013Understanding Deep Architectures using a Recursive Convolutional Networkcited by 11

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 0; 2024: 1; 2025: 1.

4 papers.

  1. 2022Super-resolution Reconstruction of Single Image for Latent featurescited by 1
  2. 2024Trustworthy SR: Resolving Ambiguity in Image Super-resolution via Diffusion Models and Human Feedbackcited by 1
  3. 2022Diverse super-resolution with pretrained deep hiererarchical VAEscited by 0
  4. 2025Enhancing Blind Face Restoration through Online Reinforcement Learningcited by 0