🚀 Awesome_GLC

Paper list of Generative Learned Compression (GLC). This includes topics such as Generative Image Compression (GIC), Generative Video Compression (GVC), Extreme Learned Image Compression (ELIC), and Extreme Learned Video Compression (ELVC) for human and machine vision perception. ELIC and ELVC, in particular, have emerged from advancements in generative models and could offer new insights into the relationship between generation ability and Shannon’s information theory. We also provide the test conditions for fair comparison.

Maintained by: Lingyu Zhu , Langxi Huang and Chengyan Jiang

Generative Image Compression Report: Chinese version

Invited Talk: Chinese version

Overview

Notes

• If you find papers relevant to this topic, please share them as a discussion post.
• Some papers may simultaneously belong to multiple subfields, and we categorize them accordingly to reflect these overlaps.
• Looking forward to your kind contributions and discussions! Many thanks!

Updated on 2026.05.09

This round prioritizes papers from TPAMI, TMM, TCSVT, IJCV, CVPR, ICCV, ECCV and closely related high-quality venues.
For very recent work, we also include arXiv / project pages when the official venue version is not yet fully indexed or the code release is only announced there.

Table of Contents

• Generative Image Compression
• Generative Video Compression
• Extreme Learned Image Compression
• Extreme Learned Video Compression
• Dataset for Human Vision Perception
• Dataset for Machine Vision Perception
• Test Conditions

Some works naturally overlap multiple categories, and we intentionally duplicate them for easier lookup.

Generative Image Compression

Publish Date	Title	Authors (First Author)	PDF	Code
2026.04	CoD-Lite: Real-Time Diffusion-Based Generative Image Compression	Bin Li et al.	2604.12525	GitHub
2026.03	DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression	Junqi Shi et al.	2603.13162	null
2026.03	ProGIC: Progressive and Lightweight Generative Image Compression with Residual Vector Quantization	Hao Cao et al.	2603.02897	null
2026.02	One-Step Diffusion for Perceptual Image Compression	Yiwen Jia et al.	2602.01570	GitHub
2025.06	Single-step Diffusion for Image Compression at Ultra-Low Bitrates	Chanung Park et al.	2506.16572	null
2025.05	Semantics-Guided Generative Image Compression	Cheng-Lin Wu et al.	2505.24015	null
2025.05	Generative Image Compression by Estimating Gradients of the Rate-variable Feature Distribution	Minghao Han et al.	2505.20984	null
2025.06	Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression	Lucas Relic et al.	CVPR 2025	null
2025.06	Decouple Distortion from Perception: Region Adaptive Diffusion for Extreme-low Bitrate Perception Image Compression	Jinchang Xu et al.	CVPR 2025	null
2025.04	Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation	Anqi Li et al.	2406.00758	GitHub
2024.09	Lossy Image Compression with Foundation Diffusion Models	Lucas Relic et al.	2404.08580	null
2024.02	MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model	Chunyi Li et al.	2402.16749	GitHub
2023.10	Towards Image Compression with Perfect Realism at Ultra-Low Bitrates	Marlene Careil et al.	2310.10325	null

Generative Video Compression

Publish Date	Title	Authors (First Author)	PDF	Code
2026.03	Generative Video Compression with One-Dimensional Latent Representation	Zihan Zheng et al.	2603.15302	Project
2026.03	ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling	Daowen Li et al.	2603.17546	null
2026.03	Generative video compression: towards 0.01% compression rate for video transmission	Xiangyu Chen et al.	Springer PDF	null
2026.01	YODA: Yet Another One-step Diffusion-based Video Compressor	Xingchen Li et al.	2601.01141	GitHub
2026.01	DiffVC-RT: Towards Practical Real-Time Diffusion-based Perceptual Neural Video Compression	Wenzhuo Ma et al.	2601.20564	null
2025.10	GIViC: Generative Implicit Video Compression	Ge Gao et al.	ICCV 2025	Project
2025.10	Diffusion Autoencoders are Foundation Video Compressors	Niccolo Niccoli et al.	ICCVW 2025	null
2025.05	Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression	Linfeng Qi et al.	2505.16177	GitHub
2025.06	Towards Practical Real-Time Neural Video Compression	Zhaoyang Jia et al.	CVPR 2025	GitHub
2019.10	Video Compression With Rate-Distortion Autoencoders	Amirhossein Habibian et al.	ICCV 2019	null
2019.10	Learned Video Compression	Oren Rippel et al.	ICCV 2019	null
2018.09	Video Compression through Image Interpolation	Chao-Yuan Wu et al.	ECCV 2018	null

Extreme Learned Image Compression

Publish Date	Title	Authors (First Author)	PDF	Code
2026.04	CoD-Lite: Real-Time Diffusion-Based Generative Image Compression	Bin Li et al.	2604.12525	GitHub
2026.02	One-Step Diffusion for Perceptual Image Compression	Yiwen Jia et al.	2602.01570	GitHub
2025.10	StableCodec: Taming One-Step Diffusion for Extreme Image Compression	Tianyu Zhang et al.	ICCV 2025	null
2025.10	DLF: Extreme Image Compression with Dual-generative Latent Fusion	Naifu Xue et al.	ICCV 2025	Project
2025.06	Single-step Diffusion for Image Compression at Ultra-Low Bitrates	Chanung Park et al.	2506.16572	null
2025.05	Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression	Linfeng Qi et al.	2505.16177	GitHub
2025.01	Toward Extreme Image Compression with Latent Feature Guidance and Diffusion Prior	Zhiyuan Li et al.	2404.18820	GitHub
2024.06	Generative Latent Coding for Ultra-Low Bitrate Image Compression	Zhaoyang Jia et al.	CVPR 2024	GitHub
2024.06	Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation	Anqi Li et al.	2406.00758	GitHub
2024.02	MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model	Chunyi Li et al.	2402.16749	GitHub
2023.10	Towards Image Compression with Perfect Realism at Ultra-Low Bitrates	Marlene Careil et al.	2310.10325	null
2023.07	Extreme Image Compression using Fine-tuned VQGANs	Qi Mao et al.	2307.08265	GitHub

Extreme Learned Video Compression

Publish Date	Title	Authors (First Author)	PDF	Code
2026.03	Generative video compression: towards 0.01% compression rate for video transmission	Xiangyu Chen et al.	Springer PDF	null
2026.03	Generative Video Compression with One-Dimensional Latent Representation	Zihan Zheng et al.	2603.15302	Project
2026.03	ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling	Daowen Li et al.	2603.17546	null
2026.01	DiffVC-RT: Towards Practical Real-Time Diffusion-based Perceptual Neural Video Compression	Wenzhuo Ma et al.	2601.20564	null
2026.01	YODA: Yet Another One-step Diffusion-based Video Compressor	Xingchen Li et al.	2601.01141	GitHub
2025.10	Diffusion Autoencoders are Foundation Video Compressors	Niccolo Niccoli et al.	ICCVW 2025	null
2025.10	GIViC: Generative Implicit Video Compression	Ge Gao et al.	ICCV 2025	Project
2025.05	Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression	Linfeng Qi et al.	2505.16177	GitHub

Dataset for Human Vision Perception

Publish Date	Title	Authors (First Author)	PDF	Code
2023.10	EvalCrafter: Benchmarking and Evaluating Large Video Generation Models	Yaofang Liu et al.	2310.11440	GitHub
2023.07	AIGCIQA2023: A Large-scale Image Quality Assessment Database for AI Generated Images: from the Perspectives of Quality, Authenticity and Correspondence	Jiarui Wang et al.	2307.00211	GitHub
2023.06	AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment	Chunyi Li et al.	2306.04717	GitHub
2019.10	KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment	Vlad Hosu et al.	1910.06180	Dataset
2019.06	KADID-10k: A Large-scale Artificially Distorted IQA Database	Hanhe Lin et al.	QoMEX 2019 PDF	Dataset
2016.09	MCL-JCV: A JND-based H.264/AVC Video Quality Assessment Dataset	Haiqiang Wang et al.	ICIP 2016	Dataset
2015.01	Image database TID2013: Peculiarities, results and perspectives	Nikolay Ponomarenko et al.	Open PDF	Dataset
2013.06	Color image database TID2013: Peculiarities and preliminary results	Nikolay Ponomarenko et al.	EUVIP 2013 PDF	Dataset

Dataset for Machine Vision Perception

Publish Date	Title	Authors (First Author)	PDF	Code
2025.03	Image Quality Assessment: From Human to Machine Preference	Chunyi Li et al.	2503.10078	GitHub
2017.06	Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering	Yash Goyal et al.	CVPR 2017	Dataset
2017.07	Scene Parsing through ADE20K Dataset	Bolei Zhou et al.	1608.05442	GitHub
2017.01	Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations	Ranjay Krishna et al.	1602.07332	Dataset
2016.04	The Cityscapes Dataset for Semantic Urban Scene Understanding	Marius Cordts et al.	1604.01685	Dataset
2015.12	ImageNet Large Scale Visual Recognition Challenge	Olga Russakovsky et al.	1409.0575	Dataset
2018.11	Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale	Alina Kuznetsova et al.	1811.00982	Dataset
2014.05	Microsoft COCO: Common Objects in Context	Tsung-Yi Lin et al.	1405.0312	Dataset

Test Conditions

• Image benchmark recommendation: Kodak, CLIC2020/CLIC2021, DIV2K, and optionally MS-COCO-30K for human preference or generative evaluation.
• Video benchmark recommendation: UVG, HEVC Class B/C/E, MCL-JCV, and clearly state low-delay or random-access settings.
• Report bitrate consistently: use bpp for images and bpp / kbps for videos; specify whether entropy coding is included.
• Report color/setup explicitly: resolution, crop policy, RGB vs. YUV, 4:4:4 vs. 4:2:0, GOP size, intra period, and frame count.
• Report both fidelity and perceptual metrics: PSNR, MS-SSIM, LPIPS, DISTS, FID, KID, and for video also FVD if applicable.
• Human/machine dual evaluation: when the method targets joint perception, additionally report downstream task performance on COCO, Cityscapes, ADE20K, VQA v2, or task-specific benchmarks.
• Runtime reporting: GPU/CPU model, precision (fp32/fp16/bf16), encoding speed, decoding speed, and whether the numbers include entropy coding.