4 papers
Enhanced Generative Machine Listener
Vishnu Raj, Gouthaman KV, Shiv Gehlot +2
We present GMLv2, a reference-based model designed for the prediction of subjective audio quality as measured by MUSHRA scores. GMLv2 introduces a Beta distribution-based loss to m…
SyncTrack4D: Cross-Video Motion Alignment and Video Synchronization for Multi-Video 4D Gaussian Splatting
Yonghan Lee, Tsung-Wei Huang, Shiv Gehlot +3
Modeling dynamic 3D scenes is challenging due to their high-dimensional nature, which requires aggregating information from multiple views to reconstruct time-evolving 3D geometry…
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…
Parametric Shadow Control for Portrait Generation in Text-to-Image Diffusion Models
Haoming Cai, Tsung-Wei Huang, Shiv Gehlot +4
Text-to-image diffusion models excel at generating diverse portraits, but lack intuitive shadow control. Existing editing approaches, as post-processing, struggle to offer effectiv…