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

arXiv: https://arxiv.org/abs/2412.00505 · HTML: https://mlsanity.com/paper/2412.00505/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 41 references that are in the map.
- First posted on arXiv 30 Nov 2024.

## Builds on (most cited first, 30 of 32)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [NeRV: Neural Representations for Videos](https://mlsanity.com/paper/2110.13903/) (2021)
- [COIN: COmpression with Implicit Neural representations](https://mlsanity.com/paper/2103.03123/) (2021)
- [Lossy Image Compression with Conditional Diffusion Models](https://mlsanity.com/paper/2209.06950/) (2022)
- [Implicit Neural Representations for Image Compression](https://mlsanity.com/paper/2112.04267/) (2021)
- [Variable Bitrate Neural Fields](https://mlsanity.com/paper/2206.07707/) (2022)
- [MLIC: Multi-Reference Entropy Model for Learned Image Compression](https://mlsanity.com/paper/2211.07273/) (2022)
- [COIN++: Neural Compression Across Modalities](https://mlsanity.com/paper/2201.12904/) (2022)
- [HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation](https://mlsanity.com/paper/2306.09818/) (2023)
- [C3: High-performance and low-complexity neural compression from a single image or video](https://mlsanity.com/paper/2312.02753/) (2023)
- [EML-NET:An Expandable Multi-Layer NETwork for Saliency Prediction](https://mlsanity.com/paper/1805.01047/) (2018)
- [COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codec](https://mlsanity.com/paper/2212.05458/) (2022)
- [NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modeling](https://mlsanity.com/paper/2212.14593/) (2022)
- [FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos](https://mlsanity.com/paper/2212.12294/) (2022)
- [Compressing multidimensional weather and climate data into neural networks](https://mlsanity.com/paper/2210.12538/) (2022)
- [NVRC: Neural Video Representation Compression](https://mlsanity.com/paper/2409.07414/) (2024)
- [An Unsupervised Information-Theoretic Perceptual Quality Metric](https://mlsanity.com/paper/2006.06752/) (2020)
- [Compression with Bayesian Implicit Neural Representations](https://mlsanity.com/paper/2305.19185/) (2023)
- [Meta-Learning Sparse Compression Networks](https://mlsanity.com/paper/2205.08957/) (2022)
- [Modality-Agnostic Variational Compression of Implicit Neural Representations](https://mlsanity.com/paper/2301.09479/) (2023)
- [On Quantizing Implicit Neural Representations](https://mlsanity.com/paper/2209.01019/) (2022)
- [PNVC: Towards Practical INR-based Video Compression](https://mlsanity.com/paper/2409.00953/) (2024)
- [Low-complexity Overfitted Neural Image Codec](https://mlsanity.com/paper/2307.12706/) (2023)
- [Cool-chic video: Learned video coding with 800 parameters](https://mlsanity.com/paper/2402.03179/) (2024)
- [RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations](https://mlsanity.com/paper/2309.17182/) (2023)

## Built on by (most cited first, 13 of 13)

- [Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Textures](https://mlsanity.com/paper/2602.05213/) (2026)
- [DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression](https://mlsanity.com/paper/2603.13162/) (2026)
- [What Matters in Practical Learned Image Compression](https://mlsanity.com/paper/2605.05148/) (2026)
- [Efficient Bayesian Inference from Noisy Pairwise Comparisons](https://mlsanity.com/paper/2510.09333/) (2025)
- [Drop-In Perceptual Optimization for 3D Gaussian Splatting](https://mlsanity.com/paper/2603.23297/) (2026)
- [Image Coding for Machines via Feature-Preserving Rate-Distortion Optimization](https://mlsanity.com/paper/2504.02216/) (2025)
- [Advances in Diffusion-Based Generative Compression](https://mlsanity.com/paper/2601.18932/) (2026)
- [Keep It Real: Challenges in Attacking Compression-Based Adversarial Purification](https://mlsanity.com/paper/2508.05489/) (2025)
- [A Mamba-based Perceptual Loss Function for Learning-based UGC Transcoding](https://mlsanity.com/paper/2603.25566/) (2026)
- [Seeing What Matters: Perceptual Wrapper with Common Randomness for 3D Gaussian Splatting](https://mlsanity.com/paper/2606.11782/) (2026)
- [Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos](https://mlsanity.com/paper/2606.19156/) (2026)
- [JPEG AIC2026: A large-scale dataset for fine-grained assessment of image coding](https://mlsanity.com/paper/2607.22783/) (2026)
- [From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality Assessment](https://mlsanity.com/paper/2609.07346/) (2026)

## Abstract (arXiv)

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.