SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting

Autor:	Kim, Hoon, Jang, Minje, Yoon, Wonjun, Lee, Jisoo, Na, Donghyun, Woo, Sanghyun
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	We introduce a co-designed approach for human portrait relighting that combines a physics-guided architecture with a pre-training framework. Drawing on the Cook-Torrance reflectance model, we have meticulously configured the architecture design to precisely simulate light-surface interactions. Furthermore, to overcome the limitation of scarce high-quality lightstage data, we have developed a self-supervised pre-training strategy. This novel combination of accurate physical modeling and expanded training dataset establishes a new benchmark in relighting realism. Comment: CVPR2024. Live demos available at https://www.beeble.ai/
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.18848 Zobrazit plný text záznamu View this record from Arxiv