6 papers
Low-Bitrate Video Compression through Semantic-Conditioned Diffusion
Lingdong Wang, Guan-Ming Su, Divya Kothandaraman +3
Traditional video codecs optimized for pixel fidelity collapse at ultra-low bitrates and produce severe artifacts. This failure arises from a fundamental misalignment between pixel…
Zero-Shot Personalized Camera Motion Control for Image-to-Video Synthesis
Pooja Guhan, Divya Kothandaraman, Geonsun Lee +3
Specifying nuanced and compelling camera motion remains a significant hurdle for non-expert creators using generative tools, creating an "expressive gap" where generic text prompts…
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…
INT-DTT+: Low-Complexity Data-Dependent Transforms for Video Coding
Samuel Fernández-Menduiña, Eduardo Pavez, Antonio Ortega +4
Discrete trigonometric transforms (DTTs), such as the DCT-2 and the DST-7, are widely used in video codecs for their balance between coding performance and computational efficiency…
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…
V-Trans4Style: Visual Transition Recommendation for Video Production Style Adaptation
Pooja Guhan, Tsung-Wei Huang, Guan-Ming Su +2
We introduce V-Trans4Style, an innovative algorithm tailored for dynamic video content editing needs. It is designed to adapt videos to different production styles like documentari…