mlsanityData to 14 Oct 2026

Lossy Image Compression with Compressive Autoencoders

arXiv 1703.00395 ↗First posted 1 Mar 2017stat.ML cs.CVcited by 294

Not on the map. Why?

Abstract (arXiv)

We propose a new approach to the problem of optimizing autoencoders for lossy image compression. New media formats, changing hardware technology, as well as diverse requirements and content types create a need for compression algorithms which are more flexible than existing codecs. Autoencoders have the potential to address this need, but are difficult to optimize directly due to the inherent non-differentiabilty of the compression loss. We here show that minimal changes to the loss are sufficient to train deep autoencoders competitive with JPEG 2000 and outperforming recently proposed approaches based on RNNs. Our network is furthermore computationally efficient thanks to a sub-pixel architecture, which makes it suitable for high-resolution images. This is in contrast to previous work on autoencoders for compression using coarser approximations, shallower architectures, computationally expensive methods, or focusing on small images.

Key facts. Cited by 294 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 60; 2022: 69; 2023: 57; 2024: 56; 2025: 36; 2026: 16.

294 papers.

Sort:

By area:

  1. 2023Finite Scalar Quantization: VQ-VAE Made Simplecited by 440
  2. 2021Deep Contextual Video Compressioncited by 221
  3. 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 202
  4. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 170
  5. 2021FVC: A New Framework towards Deep Video Compression in Feature Spacecited by 153
  6. 2022Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compressioncited by 128
  7. 2022Entroformer: A Transformer-based Entropy Model for Learned Image Compressioncited by 107
  8. 2021Enhanced Invertible Encoding for Learned Image Compressioncited by 105
  9. 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Modelscited by 94
  10. 2021Semantic Communications: Principles and Challengescited by 91
  11. 2022Lossy Compression with Gaussian Diffusioncited by 90
  12. 2022MLIC: Multi-Reference Entropy Model for Learned Image Compressioncited by 84
38 more
  1. 2022COIN++: Neural Compression Across Modalitiescited by 82
  2. 2022Multi-Realism Image Compression with a Conditional Generatorcited by 80
  3. 2025Towards Practical Real-Time Neural Video Compressioncited by 80
  4. 2022An Introduction to Neural Data Compressioncited by 79
  5. 2022VCT: A Video Compression Transformercited by 74
  6. 2022SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantizationcited by 68
  7. 2023Text + Sketch: Image Compression at Ultra Low Ratescited by 67
  8. 2023MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compressioncited by 58
  9. 2022Coarse-to-fine Deep Video Coding with Hyperprior-guided Mode Predictioncited by 55
  10. 2023C3: High-performance and low-complexity neural compression from a single image or videocited by 55
  11. 2021Joint Global and Local Hierarchical Priors for Learned Image Compressioncited by 54
  12. 2021Lossy Compression for Lossless Predictioncited by 52
  13. 2021Implicit Neural Video Compressioncited by 52
  14. 2021Soft then Hard: Rethinking the Quantization in Neural Image Compressioncited by 51
  15. 2021Optimal Representations for Covariate Shiftcited by 51
  16. 2022NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modelingcited by 51
  17. 2023On the De-duplication of LAION-2Bcited by 47
  18. 2024ElasticTok: Adaptive Tokenization for Image and Videocited by 46
  19. 2023Disentanglement via Latent Quantizationcited by 40
  20. 2021Slimmable Compressive Autoencoders for Practical Neural Image Compressioncited by 39
  21. 2021Overfitting for Fun and Profit: Instance-Adaptive Data Compressioncited by 38
  22. 2022Towards Semantic Communications: Deep Learning-Based Image Semantic Codingcited by 36
  23. 2021Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modulescited by 35
  24. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 35
  25. 2023A Residual Diffusion Model for High Perceptual Quality Codec Augmentationcited by 35
  26. 2024Image-GS: Content-Adaptive Image Representation via 2D Gaussianscited by 35
  27. 2022Image Compression with Product Quantized Masked Image Modelingcited by 33
  28. 2021Supervised Compression for Resource-Constrained Edge Computing Systemscited by 31
  29. 2023SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representationscited by 31
  30. 2023Extreme Image Compression using Fine-tuned VQGANscited by 29
  31. 2021Defending Against Image Corruptions Through Adversarial Augmentationscited by 28
  32. 2025Compressed Image Generation with Denoising Diffusion Codebook Modelscited by 28
  33. 2023HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayescited by 27
  34. 2021Towards End-to-End Image Compression and Analysis with Transformerscited by 26
  35. 2021DPICT: Deep Progressive Image Compression Using Trit-Planescited by 25
  36. 2023Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Modelcited by 25
  37. 2023Compression with Bayesian Implicit Neural Representationscited by 25
  38. 2021Variable-rate discrete representation learningcited by 24

50 most cited of 294 All 294 (JSON)