Generative Human Video Compression With Multi-Granularity Temporal Trajectory Factorization

doi:10.1109/TCSVT.2025.3596815

Generative Human Video Compression With Multi-Granularity Temporal Trajectory Factorization

2025-08-07

0

PRE

AI

DOI：10.1109/TCSVT.2025.3596815

Original

Original request for help

Save

Abstract

En 中文

In this paper, we propose a novel Multi-granularity Temporal Trajectory Factorization (MTTF) framework for generative human video compression, which holds great potential for bandwidth-constrained human-centric video communication. In particular, the proposed multi-granularity feature factorization strategy can facilitate to implicitly characterize the high-dimensional visual signal into compact motion vectors for representation compactness and further transform these vectors into fine-grained fields for motion expressibility. As such, the coded bit-stream can be entailed with enough visual motion information at the lowest representation cost. Meanwhile, a resolution-expandable generative module is developed with enhanced background stability, such that the proposed framework can be optimized towards higher reconstruction robustness and more flexible resolution adaptation. Experimental results show that proposed method outperforms latest generative models and the state-of-the-art video coding standard Versatile Video Coding (VVC) on both talking-face videos and moving-body videos in terms of both objective and subjective quality. The project page can be found at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/xyzysz/Extreme-Human-Video-Compression-with-MTTF</uri>

Keywords:

Video coding

generative model

temporal trajectory

deep animation

Generative Human Video Compression With Multi-Granularity Temporal Trajectory Factorization

Abstract

Journal

Organization