# Learning True Rate-Distortion-Optimization for End-To-End Image Compression

arXiv: https://arxiv.org/abs/2201.01586 · HTML: https://mlsanity.com/paper/2201.01586/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 5 Jan 2022.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [Density Modeling of Images using a Generalized Normalization Transformation](https://mlsanity.com/paper/1511.06281/) (2015)
- [A Technical Overview of AV1](https://mlsanity.com/paper/2008.06091/) (2020)
- [Deep Learning-based Image Compression with Trellis Coded Quantization](https://mlsanity.com/paper/2001.09417/) (2020)

## Built on by (most cited first, 1 of 1)

- [Multiscale Augmented Normalizing Flows for Image Compression](https://mlsanity.com/paper/2305.05451/) (2023)

## Abstract (arXiv)

Even though rate-distortion optimization is a crucial part of traditional image and video compression, not many approaches exist which transfer this concept to end-to-end-trained image compression. Most frameworks contain static compression and decompression models which are fixed after training, so efficient rate-distortion optimization is not possible. In a previous work, we proposed RDONet, which enables an RDO approach comparable to adaptive block partitioning in HEVC. In this paper, we enhance the training by introducing low-complexity estimations of the RDO result into the training. Additionally, we propose fast and very fast RDO inference modes. With our novel training method, we achieve average rate savings of 19.6% in MS-SSIM over the previous RDONet model, which equals rate savings of 27.3% over a comparable conventional deep image coder.