Presentation

<
Pixel Cube: Diffusion-based Portrait Video Relighting Through Realistic Lighting Reproduction
SessionFilm/VFX Production
DescriptionPixel Cube is a novel lighting system for realistic lighting emulation and high-speed video relighting data acquisition. With a high-quality lighting-aware dataset, we train a diffusion model for dynamic portrait relighting. Our model produces photorealistic, temporally consistent portrait videos under new lighting conditions that faithfully preserve the subject's facial features.
Authors
Yufan Zhang
George Mason University
Yu Ji
LightThought LLC
Ayo Ajiboye
George Mason University
Rundi Wu
Columbia University
Yu Guo
George Mason University
Changxi Zheng
Columbia University
Jinwei Ye
George Mason University
Event Type
Technical Paper
TimeWednesday, 22 July 20262:10pm - 2:20pm PDT
LocationRoom 408 B
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Wednesday, 22 July 20262:00pm - 3:30pm PDTRoom 408 B
Keywords
Generative AI
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationEasyVFX: Frequency-Driven Decoupling for Resource-Efficient VFX Generation
Similar Presentations
BodyReLux: Temporally Consistent Full-Body Video Relighting
GR3EN: Generative Relighting for 3D Environments
Relit-LiVE: Relight Video by Jointly Learning Environment Video