all AI news
SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting
March 1, 2024, 5:46 a.m. | Hoon Kim, Minje Jang, Wonjun Yoon, Jisoo Lee, Donghyun Na, Sanghyun Woo
cs.CV updates on arXiv.org arxiv.org
Abstract: 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.
abstract architecture arxiv cook cs.cv design framework human interactions light physics pre-training surface training type
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote