SwitchLight: Co-Design of Physics-Driven Architecture and Pre-training Framework for Human Portrait Relighting
Authors:
Top Cited Papers
- 16 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 25096-25106
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.Keywords
This publication has 46 references indexed in Scilit:
- Relighting4D: Neural Relightable Human from Videos2022
- Geometry-Aware Single-Image Full-Body Human Relighting2022
- A Style-Based Generator Architecture for Generative Adversarial Networks2019
- Image Inpainting for Irregular Holes Using Partial Convolutions2018
- SfSNet: Learning Shape, Reflectance and Illuminance of Faces 'in the Wild'2018
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles2016
- Colorful Image Colorization2016
- Context Encoders: Feature Learning by Inpainting2016
- Interactive design of complex time dependent lightingIEEE Computer Graphics and Applications, 1995