# Computationally Efficient Neural Image Compression

arXiv: https://arxiv.org/abs/1912.08771 · HTML: https://mlsanity.com/paper/1912.08771/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2019.

## Built on by (most cited first, 30 of 32)

- [Checkerboard Context Model for Efficient Learned Image Compression](https://mlsanity.com/paper/2103.15306/) (2021)
- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [ELF-VC: Efficient Learned Flexible-Rate Video Coding](https://mlsanity.com/paper/2104.14335/) (2021)
- [Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform](https://mlsanity.com/paper/2108.09551/) (2021)
- [C3: High-performance and low-complexity neural compression from a single image or video](https://mlsanity.com/paper/2312.02753/) (2023)
- [Lossy Compression for Lossless Prediction](https://mlsanity.com/paper/2106.10800/) (2021)
- [Slimmable Compressive Autoencoders for Practical Neural Image Compression](https://mlsanity.com/paper/2103.15726/) (2021)
- [Computationally-Efficient Neural Image Compression with Shallow Decoders](https://mlsanity.com/paper/2304.06244/) (2023)
- [Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding](https://mlsanity.com/paper/2102.11086/) (2021)
- [Exploring Autoencoder-based Error-bounded Compression for Scientific Data](https://mlsanity.com/paper/2105.11730/) (2021)
- [MobileCodec: Neural Inter-frame Video Compression on Mobile Devices](https://mlsanity.com/paper/2207.08338/) (2022)
- [Insights from Generative Modeling for Neural Video Compression](https://mlsanity.com/paper/2107.13136/) (2021)
- [Advancing The Rate-Distortion-Computation Frontier For Neural Image Compression](https://mlsanity.com/paper/2311.12821/) (2023)
- [Attention-Based Generative Neural Image Compression on Solar Dynamics Observatory](https://mlsanity.com/paper/2210.06478/) (2022)
- [CBANet: Towards Complexity and Bitrate Adaptive Deep Image Compression using a Single Network](https://mlsanity.com/paper/2105.12386/) (2021)
- [Universal Efficient Variable-rate Neural Image Compression](https://mlsanity.com/paper/2111.11305/) (2021)
- [End-to-end optimized image compression with competition of prior distributions](https://mlsanity.com/paper/2111.09172/) (2021)
- [End-to-End Learned Image Compression with Quantized Weights and Activations](https://mlsanity.com/paper/2111.09348/) (2021)
- [Exploring Structural Sparsity in Neural Image Compression](https://mlsanity.com/paper/2202.04595/) (2022)
- [Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain](https://mlsanity.com/paper/2203.16357/) (2022)
- [Identity Preserving Loss for Learned Image Compression](https://mlsanity.com/paper/2204.10869/) (2022)
- [Neural Image Compression: Generalization, Robustness, and Spectral Biases](https://mlsanity.com/paper/2307.08657/) (2023)
- [Learning sparse auto-encoders for green AI image coding](https://mlsanity.com/paper/2209.04448/) (2022)
- [COSMIC: Compress Satellite Images Efficiently via Diffusion Compensation](https://mlsanity.com/paper/2410.01698/) (2024)
- [DANICE: Domain adaptation without forgetting in neural image compression](https://mlsanity.com/paper/2104.09370/) (2021)
- [Deep learning based Image Compression for Microscopy Images: An Empirical Study](https://mlsanity.com/paper/2311.01352/) (2023)
- [Streaming-capable High-performance Architecture of Learned Image Compression Codecs](https://mlsanity.com/paper/2208.01641/) (2022)
- [Latent Discretization for Continuous-time Sequence Compression](https://mlsanity.com/paper/2212.13659/) (2022)
- [Hierarchical Autoencoder-based Lossy Compression for Large-scale High-resolution Scientific Data](https://mlsanity.com/paper/2307.04216/) (2023)
- [Neural-based Compression Scheme for Solar Image Data](https://mlsanity.com/paper/2311.02855/) (2023)

## 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.