“MetaLayer: A Meta-learned BSDF Model for Layered Materials” by Guo, Li, He, Wang, Guo, et al. …
Conference:
Type(s):
Title:
- MetaLayer: A Meta-learned BSDF Model for Layered Materials
Session/Category Title: Materials
Presenter(s)/Author(s):
Abstract:
Reproducing the appearance of arbitrary layered materials has long been a critical challenge in computer graphics, with regard to the demanding requirements of both physical accuracy and low computation cost. Recent studies have demonstrated promising results by learning-based representations that implicitly encode the appearance of complex (layered) materials by neural networks. However, existing generally-learned models often struggle between strong representation ability and high runtime performance, and also lack physical/perceptual parameters for material editing. To address these concerns, we introduce MetaLayer, a new methodology leveraging meta-learning for modeling and rendering layered materials. MetaLayer contains two networks: a BSDFNet that compactly encodes the appearance of layered materials, and a MetaNet that establishes the mapping between the physical parameters of each material and the weights of its corresponding implicit neural representation. A new positional encoding method and a well-designed training strategy are employed to improve the performance and quality of the neural model. As a new learning-based representation, the proposed MetaLayer model provides both fast responses to material editing and high-quality results for a wide range of layered materials, outperforming existing layered BSDF models.
