Session
Text-to-Image & Customization
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
| 9:00am - 9:10am HKT |  | ConsiStyle: Style Diversity in Training-Free Consistent T2I Generation | |
| 9:10am - 9:21am HKT |  | Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models | |
| 9:21am - 9:32am HKT |  | PractiLight: Practical Light Control Using Foundational Diffusion Models | |
| 9:32am - 9:43am HKT |  | Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos Technical Papers Fast Forward Presenter | |
| 9:43am - 9:54am HKT |  | Zero-Shot Dynamic Concept Personalization with Grid-Based LoRA | |
| 9:54am - 10:05am HKT |  | B4M: Breaking Low-Rank Adapter for Making Content-Style Customization Technical Papers Fast Forward Presenter |
Event Type
Technical Papers
TimeThursday, 18 December 20259:00am - 10:05am HKT
LocationMeeting Room S423+S424, Level 4
