# Learning End-to-End Lossy Image Compression: A Benchmark

arXiv: https://arxiv.org/abs/2002.03711 · HTML: https://mlsanity.com/paper/2002.03711/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2020.

## Built on by (most cited first, 30 of 60)

- [Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules](https://mlsanity.com/paper/2107.06463/) (2021)
- [Image-GS: Content-Adaptive Image Representation via 2D Gaussians](https://mlsanity.com/paper/2407.01866/) (2024)
- [QARV: Quantization-Aware ResNet VAE for Lossy Image Compression](https://mlsanity.com/paper/2302.08899/) (2023)
- [Neural Data-Dependent Transform for Learned Image Compression](https://mlsanity.com/paper/2203.04963/) (2022)
- [Towards End-to-End Image Compression and Analysis with Transformers](https://mlsanity.com/paper/2112.09300/) (2021)
- [Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuning](https://mlsanity.com/paper/2112.08691/) (2021)
- [Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression](https://mlsanity.com/paper/2209.04847/) (2022)
- [ANFIC: Image Compression Using Augmented Normalizing Flows](https://mlsanity.com/paper/2107.08470/) (2021)
- [High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregation](https://mlsanity.com/paper/2204.11448/) (2022)
- [LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks](https://mlsanity.com/paper/2111.08988/) (2021)
- [RGB no more: Minimally-decoded JPEG Vision Transformers](https://mlsanity.com/paper/2211.16421/) (2022)
- [Raw Image Reconstruction with Learned Compact Metadata](https://mlsanity.com/paper/2302.12995/) (2023)
- [Multi-Modality Deep Network for Extreme Learned Image Compression](https://mlsanity.com/paper/2304.13583/) (2023)
- [NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation](https://mlsanity.com/paper/2404.02185/) (2024)
- [Learning-Driven Lossy Image Compression; A Comprehensive Survey](https://mlsanity.com/paper/2201.09240/) (2022)
- [Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility](https://mlsanity.com/paper/2207.04895/) (2022)
- [Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation](https://mlsanity.com/paper/2309.02529/) (2023)
- [Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior](https://mlsanity.com/paper/2412.01646/) (2024)
- [Q-LIC: Quantizing Learned Image Compression with Channel Splitting](https://mlsanity.com/paper/2205.14510/) (2022)
- [Rate-Distortion Optimized Post-Training Quantization for Learned Image Compression](https://mlsanity.com/paper/2211.02854/) (2022)
- [High-Fidelity Variable-Rate Image Compression via Invertible Activation Transformation](https://mlsanity.com/paper/2209.05054/) (2022)
- [Beyond Learned Metadata-based Raw Image Reconstruction](https://mlsanity.com/paper/2306.12058/) (2023)
- [Generalized Gaussian Model for Learned Image Compression](https://mlsanity.com/paper/2411.19320/) (2024)
- [OSLO: On-the-Sphere Learning for Omnidirectional images and its application to 360-degree image compression](https://mlsanity.com/paper/2107.09179/) (2021)
- [Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling](https://mlsanity.com/paper/2211.06797/) (2022)
- [Rate Distortion Characteristic Modeling for Neural Image Compression](https://mlsanity.com/paper/2106.12954/) (2021)
- [Learned Image Compression with Generalized Octave Convolution and Cross-Resolution Parameter Estimation](https://mlsanity.com/paper/2209.03353/) (2022)
- [Sandwiched Video Compression: Efficiently Extending the Reach of Standard Codecs with Neural Wrappers](https://mlsanity.com/paper/2303.11473/) (2023)
- [GroupedMixer: An Entropy Model with Group-wise Token-Mixers for Learned Image Compression](https://mlsanity.com/paper/2405.01170/) (2024)
- [Reducing Redundancy in the Bottleneck Representation of the Autoencoders](https://mlsanity.com/paper/2202.04629/) (2022)

## Abstract (arXiv)

Image compression is one of the most fundamental techniques and commonly used applications in the image and video processing field. Earlier methods built a well-designed pipeline, and efforts were made to improve all modules of the pipeline by handcrafted tuning. Later, tremendous contributions were made, especially when data-driven methods revitalized the domain with their excellent modeling capacities and flexibility in incorporating newly designed modules and constraints. Despite great progress, a systematic benchmark and comprehensive analysis of end-to-end learned image compression methods are lacking. In this paper, we first conduct a comprehensive literature survey of learned image compression methods. The literature is organized based on several aspects to jointly optimize the rate-distortion performance with a neural network, i.e., network architecture, entropy model and rate control. We describe milestones in cutting-edge learned image-compression methods, review a broad range of existing works, and provide insights into their historical development routes. With this survey, the main challenges of image compression methods are revealed, along with opportunities to address the related issues with recent advanced learning methods. This analysis provides an opportunity to take a further step towards higher-efficiency image compression. By introducing a coarse-to-fine hyperprior model for entropy estimation and signal reconstruction, we achieve improved rate-distortion performance, especially on high-resolution images. Extensive benchmark experiments demonstrate the superiority of our model in rate-distortion performance and time complexity on multi-core CPUs and GPUs. Our project website is available at https://huzi96.github.io/compression-bench.html.