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 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 layered materials into implicit neural representations, 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.

The RPC (Rational Polynomial Coefficient) model can be used as a replacement sensor model for geo-coding spaceborne SAR data. A hybrid method, combining the L-curve and the IMCCV (Iteration method by correcting characteristic value) method, for solving ill-conditioned equations in the RPC model is proposed. The hybrid method can get higher accuracy at low cost of calculation time. Based on an example in Malaysia, the application for fast RPC geocoding for stereo radargrammetry is shown.