SwitchLight: Co-Design of Physics-Driven Architecture and Pre-training Framework for Human Portrait Relighting

Hoon Kim, Minje Jang, Wonjun Yoon, Jisoo Lee, Donghyun Na, Sanghyun Woo

Abstract: We introduce a co-designed approach for human portrait relighting that combines a physics-guided architecture with a pretraining 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 pretraining strategy. This novel combination of accurate physical modeling and expanded training dataset establishes a new benchmark in relighting realism.