collaborators

6 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…

eess.IV2025

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…

cs.CV2025

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…

cs.CV2025

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…