Real-Time Neural BRDF with Spherically Distributed Primitives
This addresses the challenge of efficient material representation for real-time rendering applications in computer graphics, though it appears incremental as it builds on existing neural BRDF approaches with optimizations for speed and memory.
The paper tackles the problem of real-time rendering of diverse materials by proposing a compact neural BRDF representation that projects bidirectional reflectance into low-dimensional hemisphere feature-grids and uses learnable neural reflectance primitives distributed on spherical surface grids. The system achieves real-time rendering at full HD resolution on current desktop machines with versatile material representation while consuming very-light memory and computation.
We propose a novel compact and efficient neural BRDF offering highly versatile material representation, yet with very-light memory and neural computation consumption towards achieving real-time rendering. The results in Figure 1, rendered at full HD resolution on a current desktop machine, show that our system achieves real-time rendering with a wide variety of appearances, which is approached by the following two designs. On the one hand, noting that bidirectional reflectance is distributed in a very sparse high-dimensional subspace, we propose to project the BRDF into two low-dimensional components, i.e., two hemisphere feature-grids for incoming and outgoing directions, respectively. On the other hand, learnable neural reflectance primitives are distributed on our highly-tailored spherical surface grid, which offer informative features for each component and alleviate the conventional heavy feature learning network to a much smaller one, leading to very fast evaluation. These primitives are centrally stored in a codebook and can be shared across multiple grids and even across materials, based on the low-cost indices stored in material-specific spherical surface grids. Our neural BRDF, which is agnostic to the material, provides a unified framework that can represent a variety of materials in consistent manner. Comprehensive experimental results on measured BRDF compression, Monte Carlo simulated BRDF acceleration, and extension to spatially varying effect demonstrate the superior quality and generalizability achieved by the proposed scheme.