Abstract Path tracing remains the gold standard for high‐fidelity subsurface scattering despite requiring numerous paths for noise‐free estimates. We introduce a novel variance‐reduction method based on two complementary zero‐variance‐theory‐based approaches. The first one, analytical Dwivedi sampling, is lightweight but struggles with complex lighting. The second one, surface path guiding, learns incident illumination at boundaries to guide sampled paths, but it does not reduce variance from subsurface scattering. In our novel method, we enhance Dwivedi sampling by incorporating the radiance field learned only at the volume boundary. We use the average normal of points on an illuminated boundary region or directions sampled from distributions of incident light at the boundary as our analytical Dwivedi slab normals. Unlike previous methods based on Dwivedi sampling, our method is efficient even in scenes with complex light rigs typical for movie production and under indirect illumination. We achieve comparable noise reduction and even slightly improved estimates in some scenes compared to volume path guiding, and our method can be easily added on top of any existing surface path guiding system. Our method is particularly effective for homogeneous, isotropic media, bypassing the extensive training and caching inside the 3D volume that volume path guiding requires.

Abstract We present Optimised Path Space Regularisation (OPSR), a novel regularisation technique for forward path tracing algorithms. Our regularisation controls the amount of roughness added to materials depending on the type of sampled paths and trades a small error in the estimator for a drastic reduction of variance in difficult paths, including indirectly visible caustics. We formulate the problem as a joint bias‐variance minimisation problem and use differentiable rendering to optimise our model. The learnt parameters generalise to a large variety of scenes irrespective of their geometric complexity. The regularisation added to the underlying light transport algorithm naturally allows us to handle the problem of near‐specular and glossy path chains robustly. Our method consistently improves the convergence of path tracing estimators, including state‐of‐the‐art path guiding techniques where it enables finding otherwise hard‐to‐sample paths and thus, in turn, can significantly speed up the learning of guiding distributions.

The human visual system is sensitive to relative differences in luminance, but light transport simulation algorithms based on Metropolis sampling often result in a highly nonuniform relative error distribution over the rendered image. Although this issue has previously been addressed in the context of the Metropolis light transport algorithm, our work focuses on Metropolis photon tracing. We present a new target function (TF) for Metropolis photon tracing that ensures good stratification of photons leading to pixel estimates with equalized relative error. We develop a hierarchical scheme for progressive construction of the TF from paths sampled during rendering. In addition to the approach taken in previous work, where the TF is defined in the image plane, ours can be associated with compact spatial regions. This allows us to take advantage of illumination coherence to more robustly estimate the TF while adapting to geometry discontinuities. To sample from this TF, we design a new replica exchange Metropolis scheme. We apply our algorithm in progressive photon mapping and show that it often outperforms alternative approaches in terms of image quality by a large margin.

The efficiency of Monte Carlo algorithms for light transport simulation is directly related to their ability to importance-sample the product of the illumination and reflectance in the rendering equation. Since the optimal sampling strategy would require knowledge about the transport solution itself, importance sampling most often follows only one of the known factors – BRDF or an approximation of the incident illumination. To address this issue, we propose to represent the illumination and the reflectance factors by the Gaussian mixture model (GMM), which we fit by using a combination of weighted expectation maximization and non-linear optimization methods. The GMM representation then allows us to obtain the resulting product distribution for importance sampling on-the-fly at each scene point. For its efficient evaluation and sampling we preform an up-front adaptive decimation of both factor mixtures. In comparison to state-of-the-art sampling methods, we show that our product importance sampling can lead to significantly better convergence in scenes with complex illumination and reflectance.

While Russian roulette (RR) and splitting are considered fundamental importance sampling techniques in neutron transport simulations, they have so far received relatively little attention in light transport. In computer graphics, RR and splitting are most often based solely on local reflectance properties. However, this strategy can be far from optimal in common scenes with non-uniform light distribution as it does not accurately predict the actual path contribution. In our approach, like in neutron transport, we estimate the expected contribution of a path as the product of the path weight and a pre-computed estimate of the adjoint transport solution. We use this estimate to generate so-called weight window which keeps the path contribution roughly constant through RR and splitting. As a result, paths in unimportant regions tend to be terminated early while in the more important regions they are spawned by splitting. This results in substantial variance reduction in both path tracing and photon tracing-based simulations. Furthermore, unlike the standard computer graphics RR, our approach does not interfere with importance-driven sampling of scattering directions, which results in superior convergence when such a technique is combined with our approach. We provide a justification of this behavior by relating our approach to the zero-variance random walk theory.

Monte Carlo techniques for light transport simulation rely on importance sampling when constructing light transport paths. Previous work has shown that suitable sampling distributions can be recovered from particles distributed in the scene prior to rendering. We propose to represent the distributions by a parametric mixture model trained in an on-line (i.e. progressive) manner from a potentially infinite stream of particles. This enables recovering good sampling distributions in scenes with complex lighting, where the necessary number of particles may exceed available memory. Using these distributions for sampling scattering directions and light emission significantly improves the performance of state-of-the-art light transport simulation algorithms when dealing with complex lighting.