Session
Dynamic Generative Video: From Synthesis to Real-Time Editing
Session Chair
DescriptionThe Technical Papers program is the heartbeat of SIGGRAPH Asia, spotlighting world-class scholarly research at the forefront of computer graphics and interactive techniques. For decades, it has been the definitive venue where bold ideas take root, foundational concepts are reimagined, and the future of visual computing is shaped.
This year, we explore new intersections of algorithms and artistry, automation and authorship, tools and imagination – challenging the very way we design, simulate, visualize, and interact with digital worlds.
This year, we explore new intersections of algorithms and artistry, automation and authorship, tools and imagination – challenging the very way we design, simulate, visualize, and interact with digital worlds.
Presentations
| 1:10pm - 1:20pm HKT | ![]() | Navigating with Annealing Guidance Scale in Diffusion Space | |
| 1:20pm - 1:31pm HKT | ![]() | Input-Aware Sparse Attention for Real-Time Co-Speech Video Generation | |
| 1:31pm - 1:42pm HKT | ![]() | OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion Models | |
| 1:42pm - 1:53pm HKT | ![]() | STGlight: Online Indoor Lighting Estimation via Spatio-Temporal Gaussian Fusion | |
| 1:53pm - 2:04pm HKT | ![]() | GenLit: Reformulating Single-Image Relighting as Video Generation | |
| 2:04pm - 2:15pm HKT | ![]() | DynVFX: Augmenting Real Videos with Dynamic Content |
Event Type
Technical Papers
TimeMonday, 15 December 20251:10pm - 2:15pm HKT
LocationMeeting Room S423+S424, Level 4








