mlsanityData to 7 Oct 2026

Computationally Efficient Neural Image Compression

arXiv 1912.08771 ↗First posted 18 Dec 2019eess.IV cs.LG stat.MLcited by 31

Not on the map. Why?

Abstract (arXiv)

Image compression using neural networks have reached or exceeded non-neural methods (such as JPEG, WebP, BPG). While these networks are state of the art in ratedistortion performance, computational feasibility of these models remains a challenge. We apply automatic network optimization techniques to reduce the computational complexity of a popular architecture used in neural image compression, analyze the decoder complexity in execution runtime and explore the trade-offs between two distortion metrics, rate-distortion performance and run-time performance to design and research more computationally efficient neural image compression. We find that our method decreases the decoder run-time requirements by over 50% for a stateof-the-art neural architecture.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 13; 2022: 9; 2023: 7; 2024: 2.

31 papers.

Sort:

  1. 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 193
  2. 2022An Introduction to Neural Data Compressioncited by 78
  3. 2021ELF-VC: Efficient Learned Flexible-Rate Video Codingcited by 68
  4. 2021Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transformcited by 56
  5. 2023C3: High-performance and low-complexity neural compression from a single image or videocited by 54
  6. 2021Lossy Compression for Lossless Predictioncited by 51
  7. 2021Slimmable Compressive Autoencoders for Practical Neural Image Compressioncited by 38
  8. 2023Computationally-Efficient Neural Image Compression with Shallow Decoderscited by 22
  9. 2021Improving Lossless Compression Rates via Monte Carlo Bits-Back Codingcited by 19
  10. 2021Exploring Autoencoder-based Error-bounded Compression for Scientific Datacited by 19
  11. 2022MobileCodec: Neural Inter-frame Video Compression on Mobile Devicescited by 15
  12. 2021Insights from Generative Modeling for Neural Video Compressioncited by 9
19 more
  1. 2023Advancing The Rate-Distortion-Computation Frontier For Neural Image Compressioncited by 9
  2. 2022Attention-Based Generative Neural Image Compression on Solar Dynamics Observatorycited by 8
  3. 2021CBANet: Towards Complexity and Bitrate Adaptive Deep Image Compression using a Single Networkcited by 6
  4. 2021Universal Efficient Variable-rate Neural Image Compressioncited by 6
  5. 2021End-to-end optimized image compression with competition of prior distributionscited by 4
  6. 2022Exploring Structural Sparsity in Neural Image Compressioncited by 4
  7. 2022Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domaincited by 4
  8. 2022Identity Preserving Loss for Learned Image Compressioncited by 4
  9. 2023Neural Image Compression: Generalization, Robustness, and Spectral Biasescited by 4
  10. 2022Learning sparse auto-encoders for green AI image codingcited by 3
  11. 2024COSMIC: Compress Satellite Images Efficiently via Diffusion Compensationcited by 3
  12. 2021DANICE: Domain adaptation without forgetting in neural image compressioncited by 2
  13. 2023Deep learning based Image Compression for Microscopy Images: An Empirical Studycited by 2
  14. 2022Streaming-capable High-performance Architecture of Learned Image Compression Codecscited by 1
  15. 2023Hierarchical Autoencoder-based Lossy Compression for Large-scale High-resolution Scientific Datacited by 1
  16. 2023Neural-based Compression Scheme for Solar Image Datacited by 1
  17. 2024Region of Interest Loss for Anonymizing Learned Image Compressioncited by 1
  18. 2021DeepCompress: Efficient Point Cloud Geometry Compressioncited by 0
  19. 2022Latent Discretization for Continuous-time Sequence Compressioncited by 0