# Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein Distortion

Source: [Good, Cheap, and Fast: Overfitted Image Compression with Wasserstein Distortion](<https://www.sota2.com/research/paper/68fa77981e209131cea743fe>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-25T06:12:18.141Z

Authors: Jona Ball\\'e, Luca Versari, Emilien Dupont, Hyunjik Kim, Matthias Bauer

Published: 2024-11-30T15:05:01.000Z

## Abstract

Inspired by the success of generative image models, recent work on learned image compression increasingly focuses on better probabilistic models of the natural image distribution, leading to excellent image quality. This, however, comes at the expense of a computational complexity that is several orders of magnitude higher than today's commercial codecs, and thus prohibitive for most practical applications. With this paper, we demonstrate that by focusing on modeling visual perception rather than the data distribution, we can achieve a very good trade-off between visual quality and bit rate similar to "generative" compression models such as HiFiC, while requiring less than 1% of the multiply-accumulate operations (MACs) for decompression. We do this by optimizing C3, an overfitted image codec, for Wasserstein Distortion (WD), and evaluating the image reconstructions with a human rater study, showing that WD clearly outperforms LPIPS as an optimization objective. The study also reveals that WD outperforms other perceptual metrics such as LPIPS, DISTS, and MS-SSIM as a predictor of human ratings, remarkably achieving over 94% Pearson correlation with Elo scores.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Compression on CLIC 2020](<https://www.sota2.com/research/sota/image-compression-on-clic-2020.md>): Image Compression; CLIC 2020; BD-rate (LPIPS): -47.14.

- [Image Compression on Kodak (BD-Rate vs LPIPS/DISTS)](<https://www.sota2.com/research/sota/image-compression-on-kodak-bd-rate-vs-lpips-dists.md>): Image Compression; Kodak; BD-Rate (DISTS): 62.25.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2412.00505>)

[PDF](<https://arxiv.org/pdf/2412.00505.pdf>)