7 papers
Tokenizing Motion: A Generative Approach for Scene Dynamics Compression
Shanzhi Yin, Zihan Zhang, Bolin Chen +2
This paper proposes a novel generative video compression framework that leverages motion pattern priors, derived from subtle dynamics in common scenes (e.g., swaying flowers or a b…
Standardizing Generative Face Video Compression using Supplemental Enhancement Information
Bolin Chen, Yan Ye, Jie Chen +12
This paper proposes a Generative Face Video Compression (GFVC) approach using Supplemental Enhancement Information (SEI), where a series of compact spatial and temporal representat…
A Lightweight Dual-Mode Optimization for Generative Face Video Coding
Zihan Zhang, Shanzhi Yin, Bolin Chen +3
Generative Face Video Coding (GFVC) achieves superior rate-distortion performance by leveraging the strong inference capabilities of deep generative models. However, its practical…
Rethinking Generative Human Video Coding with Implicit Motion Transformation
Bolin Chen, Ru-Ling Liao, Jie Chen +1
Beyond traditional hybrid-based video codec, generative video codec could achieve promising compression performance by evolving high-dimensional signals into compact feature repres…
Generative Models at the Frontier of Compression: A Survey on Generative Face Video Coding
Bolin Chen, Shanzhi Yin, Goluck Konuko +4
The rise of deep generative models has greatly advanced video compression, reshaping the paradigm of face video coding through their powerful capability for semantic-aware represen…
Latent Guidance in Diffusion Models for Perceptual Evaluations
Shreshth Saini, Ru-Ling Liao, Yan Ye +1
Despite recent advancements in latent diffusion models that generate high-dimensional image data and perform various downstream tasks, there has been little exploration into percep…