# Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression

arXiv: https://arxiv.org/abs/2412.11379 · HTML: https://mlsanity.com/paper/2412.11379/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion for compression and wireless, one of 14 directions in Diffusion models.
- Builds on 10 of its 49 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Placed in

- Diffusion models / [Diffusion for compression and wireless](https://mlsanity.com/diffusion/diffusion-for-compression-and-wireless/)

## Builds on (most cited first, 10 of 10)

- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild](https://mlsanity.com/paper/2401.13627/) (2024)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior](https://mlsanity.com/paper/2308.15070/) (2023)
- [A Unified End-to-End Framework for Efficient Deep Image Compression](https://mlsanity.com/paper/2002.03370/) (2020)
- [Towards Deeper Understanding of Variational Autoencoding Models](https://mlsanity.com/paper/1702.08658/) (2017)
- [High-Fidelity Image Compression with Score-based Generative Models](https://mlsanity.com/paper/2305.18231/) (2023)
- [A Residual Diffusion Model for High Perceptual Quality Codec Augmentation](https://mlsanity.com/paper/2301.05489/) (2023)
- [Extreme Generative Image Compression by Learning Text Embedding from Diffusion Models](https://mlsanity.com/paper/2211.07793/) (2022)
- [Exploring Effective Mask Sampling Modeling for Neural Image Compression](https://mlsanity.com/paper/2306.05704/) (2023)

## Built on by (most cited first, 6 of 6)

- [GIViC: Generative Implicit Video Compression](https://mlsanity.com/paper/2503.19604/) (2025)
- [Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Textures](https://mlsanity.com/paper/2602.05213/) (2026)
- [Regularized Schr"odinger Bridge via Distortion-Perception Perturbation for High-Fidelity Speech Enhancement](https://mlsanity.com/paper/2511.11686/) (2025)
- [Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression](https://mlsanity.com/paper/2606.01608/) (2026)
- [TerraCodec: Compressing Optical Earth Observation Data](https://mlsanity.com/paper/2510.12670/) (2025)
- [Every Packet Counts: Dispersing Information for Loss-Resilient Learned Image Compression](https://mlsanity.com/paper/2608.11096/) (2026)

## Abstract (arXiv)

Neural image compression often faces a challenging trade-off among rate, distortion and perception. While most existing methods typically focus on either achieving high pixel-level fidelity or optimizing for perceptual metrics, we propose a novel approach that simultaneously addresses both aspects for a fixed neural image codec. Specifically, we introduce a plug-and-play module at the decoder side that leverages a latent diffusion process to transform the decoded features, enhancing either low distortion or high perceptual quality without altering the original image compression codec. Our approach facilitates fusion of original and transformed features without additional training, enabling users to flexibly adjust the balance between distortion and perception during inference. Extensive experimental results demonstrate that our method significantly enhances the pretrained codecs with a wide, adjustable distortion-perception range while maintaining their original compression capabilities. For instance, we can achieve more than 150% improvement in LPIPS-BDRate without sacrificing more than 1 dB in PSNR.