mlsanityData to 7 Oct 2026

Video Coding Using Learned Latent GAN Compression

arXiv 2207.04324 ↗First posted 9 Jul 2022eess.IV cs.CV stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

We propose in this paper a new paradigm for facial video compression. We leverage the generative capacity of GANs such as StyleGAN to represent and compress a video, including intra and inter compression. Each frame is inverted in the latent space of StyleGAN, from which the optimal compression is learned. To do so, a diffeomorphic latent representation is learned using a normalizing flows model, where an entropy model can be optimized for image coding. In addition, we propose a new perceptual loss that is more efficient than other counterparts. Finally, an entropy model for video inter coding with residual is also learned in the previously constructed latent representation. Our method (SGANC) is simple, faster to train, and achieves better results for image and video coding compared to state-of-the-art codecs such as VTM, AV1, and recent deep learning techniques. In particular, it drastically minimizes perceptual distortion at low bit rates.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 46 of its 74 references that are in the map. First posted on arXiv 9 Jul 2022.

Builds on

46 of 74 references.

References · 46

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  7. 2016Density estimation using Real NVPcited by 2,029
  8. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  9. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  10. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  11. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  12. 2018Variational image compression with a scale hyperpriorcited by 910
34 more
  1. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  2. 2016End-to-end Optimized Image Compressioncited by 673
  3. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  4. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  5. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  6. 2020One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencingcited by 438
  7. 2020High-Fidelity Generative Image Compressioncited by 331
  8. 2018DVC: An End-to-end Deep Video Compression Frameworkcited by 324
  9. 2021Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representationcited by 288
  10. 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
  11. 2020CompressAI: a PyTorch library and evaluation platform for end-to-end compression researchcited by 271
  12. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 221
  13. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  14. 2016Full Resolution Image Compression with Recurrent Neural Networkscited by 170
  15. 2021FVC: A New Framework towards Deep Video Compression in Feature Spacecited by 149
  16. 2017Real-Time Adaptive Image Compressioncited by 127
  17. 2020M-LVC: Multiple Frames Prediction for Learned Video Compressioncited by 106
  18. 2017Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networkscited by 91
  19. 2021Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editingcited by 91
  20. 2021HyperInverter: Improving StyleGAN Inversion via Hypernetworkcited by 85
  21. 2017Learning Convolutional Networks for Content-weighted Image Compressioncited by 73
  22. 2016End-to-end optimization of nonlinear transform codes for perceptual qualitycited by 72
  23. 2018Deep Generative Models for Distribution-Preserving Lossy Compressioncited by 59
  24. 2020Improving Deep Video Compression by Resolution-adaptive Flow Codingcited by 58
  25. 2020Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applicationscited by 48
  26. 2018Deep Convolutional AutoEncoder-based Lossy Image Compressioncited by 42
  27. 2017Generative Compressioncited by 40
  28. 2022Style Transformer for Image Inversion and Editingcited by 37
  29. 2020An Unsupervised Information-Theoretic Perceptual Quality Metriccited by 28
  30. 2020Low Bandwidth Video-Chat Compression using Deep Generative Modelscited by 24
  31. 2020Learned Video Compression with Feature-level Residualscited by 15
  32. 2019Deep Residual Learning for Image Compressioncited by 13
  33. 2021MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesiscited by 10
  34. 2020Perceptually Optimizing Deep Image Compressioncited by 4

Built on by

Cited by year

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

4 papers.

  1. 2023RQAT-INR: Improved Implicit Neural Image Compressioncited by 9
  2. 2025T-GVC: Trajectory-Guided Generative Video Coding at Ultra-Low Bitratescited by 8
  3. 2023Improved Positional Encoding for Implicit Neural Representation based Compact Data Representationcited by 4
  4. 2025Exploiting Latent Properties to Optimize Neural Codecscited by 0