Abstract
Video-streaming services usually feature post-processing effects to replace the background. However, these often yield inconsistent lighting. Machine-learning-based relighting methods can address this problem, but, at real-time rates, are restricted to a low resolution and can result in an unrealistic skin appearance. Physically-based rendering techniques require complex skin models that can only be acquired using specialised equipment. Our method is lightweight and uses only a standard smartphone. By correcting imperfections during capture, we extract a convincing physically-based skin model. In combination with suitable acceleration techniques, we achieve real-time rates on commodity hardware.
Original language | English |
---|---|
Article number | 3522626 |
Number of pages | 19 |
Journal | Proceedings of the ACM on Computer Graphics and Interactive Techniques |
Volume | 5 |
Issue number | 1 |
DOIs | |
Publication status | Published - 2022 |
Keywords
- face capture
- reflectance function
- Relighting