Multiple importance sampling (MIS) is an indispensable tool in rendering that constructs robust sampling strategies by combining the respective strengths of individual distributions. Its efficiency can be greatly improved by carefully selecting the number of samples drawn from each distribution, but automating this process remains a challenging problem. Existing works are mostly limited to mixture sampling, in which only a single sample is drawn in total, and the works that do investigate multi-sample MIS only optimize the sample counts at a per-pixel level, which cannot account for variations beyond the first bounce. Recent work on Russian roulette and splitting has demonstrated how fixed-point schemes can be used to spatially vary sample counts to optimize image efficiency but is limited to choosing the same number of samples across all sampling strategies. Our work proposes a highly flexible sample allocation strategy that bridges the gap between these areas of work. We show how to iteratively optimize the sample counts to maximize the efficiency of the rendered image using a lightweight data structure, which allows us to make local and individual decisions per technique. We demonstrate the benefits of our approach in two applications, path guiding and bidirectional path tracing, in both of which we achieve consistent and substantial speedups over the respective previous state-of-the-art.

Russian roulette and splitting are widely used techniques to increase the efficiency of Monte Carlo estimators. But, despite their popularity, there is little work on how to best apply them. Most existing approaches rely on simple heuristics based on, e.g., surface albedo and roughness. Their efficiency often hinges on user-controlled parameters. We instead iteratively learn optimal Russian roulette and splitting factors during rendering, using a simple and lightweight data structure. Given perfect estimates of variance and cost, our fixed-point iteration provably converges to the optimal Russian roulette and splitting factors that maximize the rendering efficiency. In our application to unidirectional path tracing, we achieve consistent and significant speed-ups over the state of the art.

Path guiding is a promising tool to improve the performance of path tracing algorithms. However, not much research has investigated what target densities a guiding method should strive to learn for optimal performance. Instead, most previous work pursues the zero-variance goal: The local decisions are guided under the assumption that all other decisions along the random walk will be sampled perfectly. In practice, however, many decisions are poorly guided, or not guided at all. Furthermore, learned distributions are often marginalized, e.g., by neglecting the BSDF. We present a generic procedure to derive theoretically optimal target densities for local path guiding. These densities account for variance in nested estimators, and marginalize provably well over, e.g., the BSDF. We apply our theory in two state-of-the-art rendering applications: a path guiding solution for unidirectional path tracing [Müller et al. 2017] and a guiding method for light source selection for the many lights problem [Vévoda et al. 2018]. In both cases, we observe significant improvements, especially on glossy surfaces. The implementations for both applications consist of trivial modifications to the original code base, without introducing any additional overhead.