# Better Compression with Deep Pre-Editing

arXiv: https://arxiv.org/abs/2002.00113 · HTML: https://mlsanity.com/paper/2002.00113/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Feb 2020.

## Built on by (most cited first, 9 of 9)

- [Learning to Resize Images for Computer Vision Tasks](https://mlsanity.com/paper/2103.09950/) (2021)
- [Preprocessing Enhanced Image Compression for Machine Vision](https://mlsanity.com/paper/2206.05650/) (2022)
- [High-Perceptual Quality JPEG Decoding via Posterior Sampling](https://mlsanity.com/paper/2211.11827/) (2022)
- [MULLER: Multilayer Laplacian Resizer for Vision](https://mlsanity.com/paper/2304.02859/) (2023)
- [Standard compliant video coding using low complexity, switchable neural wrappers](https://mlsanity.com/paper/2407.07395/) (2024)
- [Neural JPEG: End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder](https://mlsanity.com/paper/2201.11795/) (2022)
- [JPEG Processing Neural Operator for Backward-Compatible Coding](https://mlsanity.com/paper/2507.23521/) (2025)
- [Rate-distortion Optimized Point Cloud Preprocessing for Geometry-based Point Cloud Compression](https://mlsanity.com/paper/2508.01633/) (2025)
- [A Preprocessing Framework for Video Machine Vision under Compression](https://mlsanity.com/paper/2512.15331/) (2025)

## Abstract (arXiv)

Could we compress images via standard codecs while avoiding visible artifacts? The answer is obvious -- this is doable as long as the bit budget is generous enough. What if the allocated bit-rate for compression is insufficient? Then unfortunately, artifacts are a fact of life. Many attempts were made over the years to fight this phenomenon, with various degrees of success. In this work we aim to break the unholy connection between bit-rate and image quality, and propose a way to circumvent compression artifacts by pre-editing the incoming image and modifying its content to fit the given bits. We design this editing operation as a learned convolutional neural network, and formulate an optimization problem for its training. Our loss takes into account a proximity between the original image and the edited one, a bit-budget penalty over the proposed image, and a no-reference image quality measure for forcing the outcome to be visually pleasing. The proposed approach is demonstrated on the popular JPEG compression, showing savings in bits and/or improvements in visual quality, obtained with intricate editing effects.