ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling

2026-03-18

AI Summary

Existing learned video compression methods struggle to natively support variable bitrates and progressive transmission, and often suffer from insufficient coupling between the generative module and entropy coding, limiting overall compression efficiency. To address these limitations, this work proposes ProGVC, a unified framework that, for the first time, integrates progressive transmission, efficient entropy coding, and generative detail reconstruction within a single codec. The approach introduces a multi-scale residual token representation and leverages a Transformer-based autoregressive context model to enable coarse-to-fine progressive encoding, while jointly optimizing the generative prior and entropy coding. Experimental results demonstrate that ProGVC significantly improves perceptual quality at low bitrates and offers flexible bitrate adaptation alongside practical scalability.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Learning & Optimization for CV
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Perceptual video compression leverages generative priors to reconstruct realistic textures and motions at low bitrates. However, existing perceptual codecs often lack native support for variable bitrate and progressive delivery, and their generative modules are weakly coupled with entropy coding, limiting bitrate reduction. Inspired by the next-scale prediction in the Visual Auto-Regressive (VAR) models, we propose ProGVC, a Progressive-based Generative Video Compression framework that unifies progressive transmission, efficient entropy coding, and detail synthesis within a single codec. ProGVC encodes videos into hierarchical multi-scale residual token maps, enabling flexible rate adaptation by transmitting a coarse-to-fine subset of scales in a progressive manner. A Transformer-based multi-scale autoregressive context model estimates token probabilities, utilized both for efficient entropy coding of the transmitted tokens and for predicting truncated fine-scale tokens at the decoder to restore perceptual details. Extensive experiments demonstrate that as a new coding paradigm, ProGVC delivers promising perceptual compression performance at low bitrates while offering practical scalability at the same time.

Problem

• perceptual video compression
• variable bitrate
• progressive delivery
• entropy coding
• generative priors

Innovation

• Progressive Video Compression
• Generative Video Coding
• Auto-Regressive Context Modeling
• Multi-Scale Token Representation
• Perceptual Quality