# Compact Latent Representation for Image Compression (CLRIC)

arXiv: https://arxiv.org/abs/2502.14937 · HTML: https://mlsanity.com/paper/2502.14937/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Builds on (most cited first, 27 of 27)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [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)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [Attentive Neural Processes](https://mlsanity.com/paper/1901.05761/) (2019)
- [Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation](https://mlsanity.com/paper/2403.12015/) (2024)
- [COIN: COmpression with Implicit Neural representations](https://mlsanity.com/paper/2103.03123/) (2021)
- [Learned Image Compression with Mixed Transformer-CNN Architectures](https://mlsanity.com/paper/2303.14978/) (2023)
- [MLIC: Multi-Reference Entropy Model for Learned Image Compression](https://mlsanity.com/paper/2211.07273/) (2022)
- [Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think](https://mlsanity.com/paper/2409.11355/) (2024)
- [Transformer-based Image Compression](https://mlsanity.com/paper/2111.06707/) (2021)
- [A Unified End-to-End Framework for Efficient Deep Image Compression](https://mlsanity.com/paper/2002.03370/) (2020)
- [MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression](https://mlsanity.com/paper/2307.15421/) (2023)
- [COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codec](https://mlsanity.com/paper/2212.05458/) (2022)
- [Tutorial on Diffusion Models for Imaging and Vision](https://mlsanity.com/paper/2403.18103/) (2024)
- [Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules](https://mlsanity.com/paper/2107.06463/) (2021)
- [A Comprehensive Benchmark for Single Image Compression Artifacts Reduction](https://mlsanity.com/paper/1909.03647/) (2019)
- [Low-complexity Overfitted Neural Image Codec](https://mlsanity.com/paper/2307.12706/) (2023)
- [Generative Visual Compression: A Review](https://mlsanity.com/paper/2402.02140/) (2024)
- [Overfitted image coding at reduced complexity](https://mlsanity.com/paper/2403.11651/) (2024)

## Abstract (arXiv)

Current image compression models often require separate models for each quality level, making them resource-intensive in terms of both training and storage. To address these limitations, we propose an innovative approach that utilizes latent variables from pre-existing trained models (such as the Stable Diffusion Variational Autoencoder) for perceptual image compression. Our method eliminates the need for distinct models dedicated to different quality levels. We employ overfitted learnable functions to compress the latent representation from the target model at any desired quality level. These overfitted functions operate in the latent space, ensuring low computational complexity, around 25.5 MAC/pixel for a forward pass on images with dimensions (1363 × 2048) pixels. This approach efficiently utilizes resources during both training and decoding. Our method achieves comparable perceptual quality to state-of-the-art learned image compression models while being both model-agnostic and resolution-agnostic. This opens up new possibilities for the development of innovative image compression methods.