# High-Fidelity Image Compression with Score-based Generative Models

arXiv: https://arxiv.org/abs/2305.18231 · HTML: https://mlsanity.com/paper/2305.18231/

## Key facts

- Cited by 54 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 38 of its 47 references that are in the map.
- First posted on arXiv 26 May 2023.

## Placed in

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

## Builds on (most cited first, 30 of 38)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Simple diffusion: End-to-end diffusion for high resolution images](https://mlsanity.com/paper/2301.11093/) (2023)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [Channel-wise Autoregressive Entropy Models for Learned Image Compression](https://mlsanity.com/paper/2007.08739/) (2020)
- [Generative Adversarial Networks for Extreme Learned Image Compression](https://mlsanity.com/paper/1804.02958/) (2018)
- [Scalable Adaptive Computation for Iterative Generation](https://mlsanity.com/paper/2212.11972/) (2022)
- [On the Importance of Noise Scheduling for Diffusion Models](https://mlsanity.com/paper/2301.10972/) (2023)
- [Lossy Image Compression with Conditional Diffusion Models](https://mlsanity.com/paper/2209.06950/) (2022)
- [Real-Time Adaptive Image Compression](https://mlsanity.com/paper/1705.05823/) (2017)
- [Lossy Compression with Gaussian Diffusion](https://mlsanity.com/paper/2206.08889/) (2022)
- [Multi-Realism Image Compression with a Conditional Generator](https://mlsanity.com/paper/2212.13824/) (2022)
- [Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters](https://mlsanity.com/paper/1810.00440/) (2018)

## Built on by (most cited first, 30 of 54)

- [Towards image compression with perfect realism at ultra-low bitrates](https://mlsanity.com/paper/2310.10325/) (2023)
- [Lossy Image Compression with Foundation Diffusion Models](https://mlsanity.com/paper/2404.08580/) (2024)
- [Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization](https://mlsanity.com/paper/2503.11056/) (2025)
- [StableCodec: Taming One-Step Diffusion for Extreme Image Compression](https://mlsanity.com/paper/2506.21977/) (2025)
- [MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model](https://mlsanity.com/paper/2402.16749/) (2024)
- [Idempotence and Perceptual Image Compression](https://mlsanity.com/paper/2401.08920/) (2024)
- [Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression](https://mlsanity.com/paper/2505.16177/) (2025)
- [Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity](https://mlsanity.com/paper/2403.02944/) (2024)
- [Generative Latent Coding for Ultra-Low Bitrate Image Compression](https://mlsanity.com/paper/2512.20194/) (2025)
- [Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion](https://mlsanity.com/paper/2505.08281/) (2025)
- [Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model](https://mlsanity.com/paper/2405.16817/) (2024)
- [DORSal: Diffusion for Object-centric Representations of Scenes et al](https://mlsanity.com/paper/2306.08068/) (2023)
- [Epsilon-VAE: Denoising as Visual Decoding](https://mlsanity.com/paper/2410.04081/) (2024)
- [EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation](https://mlsanity.com/paper/2309.03244/) (2023)
- [PICD: Versatile Perceptual Image Compression with Diffusion Rendering](https://mlsanity.com/paper/2505.05853/) (2025)
- [Progressive Compression with Universally Quantized Diffusion Models](https://mlsanity.com/paper/2412.10935/) (2024)
- [PSC: Posterior Sampling-Based Compression](https://mlsanity.com/paper/2407.09896/) (2024)
- [Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression](https://mlsanity.com/paper/2504.02579/) (2025)
- [SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization](https://mlsanity.com/paper/2510.04961/) (2025)
- [Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder](https://mlsanity.com/paper/2512.12229/) (2025)
- [Extreme Video Compression with Pre-trained Diffusion Models](https://mlsanity.com/paper/2402.08934/) (2024)
- [Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression](https://mlsanity.com/paper/2412.11379/) (2024)
- [Sample what you cant compress](https://mlsanity.com/paper/2409.02529/) (2024)
- [Is JPEG AI going to change image forensics?](https://mlsanity.com/paper/2412.03261/) (2024)
- [GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow](https://mlsanity.com/paper/2603.26571/) (2026)
- [Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression](https://mlsanity.com/paper/2604.10546/) (2026)
- [High Frequency Matters: Uncertainty Guided Image Compression with Wavelet Diffusion](https://mlsanity.com/paper/2407.12538/) (2024)
- [LMM-driven Semantic Image-Text Coding for Ultra Low-bitrate Learned Image Compression](https://mlsanity.com/paper/2411.13033/) (2024)
- [Synonymous Variational Inference for Perceptual Image Compression](https://mlsanity.com/paper/2505.22438/) (2025)
- [Single-step Diffusion for Image Compression at Ultra-Low Bitrates](https://mlsanity.com/paper/2506.16572/) (2025)

## Abstract (arXiv)

Despite the tremendous success of diffusion generative models in text-to-image generation, replicating this success in the domain of image compression has proven difficult. In this paper, we demonstrate that diffusion can significantly improve perceptual quality at a given bit-rate, outperforming state-of-the-art approaches PO-ELIC and HiFiC as measured by FID score. This is achieved using a simple but theoretically motivated two-stage approach combining an autoencoder targeting MSE followed by a further score-based decoder. However, as we will show, implementation details matter and the optimal design decisions can differ greatly from typical text-to-image models.