ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling
This addresses the need for efficient, scalable video compression for applications like streaming, though it appears incremental by building on existing generative and autoregressive models.
The paper tackled the problem of perceptual video compression lacking variable bitrate and progressive delivery by proposing ProGVC, a framework that unifies progressive transmission, entropy coding, and detail synthesis, delivering promising performance at low bitrates with practical scalability.
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.