ACM Comput Graph Interact Tech

Real-Time Relighting of Human Faces with a Low-Cost Setup

Nejc Macek, Baran Usta, Elmar Eisemann, and Ricardo Marroquim

Publisher Paper Cite More

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.

More Information

Gallery

Citation

BibTex

@article{bib:macek:2022,
    author       = { Macek, Nejc and Usta, Baran and Eisemann, Elmar and Marroquim, Ricardo },    
    title        = { Real-Time Relighting of Human Faces with a Low-Cost Setup },
    journal      = { ACM Comput Graph Interact Tech },
    volume       = { 5 },
    year         = { 2022 },
    pages        = { 14:1--14:19 },
    doi          = { 10.1145/3522626 },
    dblp         = { journals/pacmcgit/MacekUEM22 },
    url          = { https://publications.graphics.tudelft.nl/papers/47 },
}