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

TL;DR

ProGVC introduces a progressive, hierarchical video compression framework that combines autoregressive context modeling with efficient entropy coding, enabling scalable, perceptually rich video reconstruction at low bitrates.

Contribution

It unifies progressive transmission, entropy coding, and detail synthesis in a single codec using hierarchical residual tokens and Transformer-based autoregressive modeling.

Findings

Achieves promising perceptual quality at low bitrates.

Supports flexible rate adaptation through multi-scale residual tokens.

Demonstrates scalability and efficiency in experimental evaluations.

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.