Neural BRDF Importance Sampling by Reparameterization
This work addresses a specific problem in computer graphics for rendering realistic materials, offering an incremental improvement over prior methods by removing constraints like invertible networks.
The paper tackles the challenge of importance sampling for neural BRDFs in physically-based rendering by introducing a reparameterization-based formulation that integrates into the standard pipeline, achieving the best variance reduction in neural BRDF renderings while maintaining high inference speeds compared to existing baselines.
Neural bidirectional reflectance distribution functions (BRDFs) have emerged as popular material representations for enhancing realism in physically-based rendering. Yet their importance sampling remains a significant challenge. In this paper, we introduce a reparameterization-based formulation of neural BRDF importance sampling that seamlessly integrates into the standard rendering pipeline with precise generation of BRDF samples. The reparameterization-based formulation transfers the distribution learning task to a problem of identifying BRDF integral substitutions. In contrast to previous methods that rely on invertible networks and multi-step inference to reconstruct BRDF distributions, our model removes these constraints, which offers greater flexibility and efficiency. Our variance and performance analysis demonstrates that our reparameterization method achieves the best variance reduction in neural BRDF renderings while maintaining high inference speeds compared to existing baselines.