Monte Carlo integration is firmly established as the basis for most practical realistic image synthesis algorithms because of its flexibility and generality. However, the visual quality of rendered images often suffers from estimator variance, which appears as visually distracting noise. Adaptive sampling and reconstruction algorithms reduce variance by controlling the sampling density and aggregating samples in a reconstruction step, possibly over large image regions. In this paper we survey recent advances in this area. We distinguish between "a priori" methods that analyze the light transport equations and derive sampling rates and reconstruction filters from this analysis, and "a posteriori" methods that apply statistical techniques to sets of samples to drive the adaptive sampling and reconstruction process. They typically estimate the errors of several reconstruction filters, and select the best filter locally to minimize error. We discuss advantages and disadvantages of recent state-of-the-art techniques, and provide visual and quantitative comparisons. Some of these techniques are proving useful in real-world applications, and we aim to provide an overview for practitioners and researchers to assess these approaches. In addition, we discuss directions for potential further improvements.
Monte Carlo ray tracing is considered one of the most effective techniques for rendering photo-realistic imagery, but requires a large number of ray samples to produce converged or even visually pleasing images. We develop a novel image-plane adaptive sampling and reconstruction method based on local regression theory. A novel local space estimation process is proposed for employing the local regression, by robustly addressing noisy high-dimensional features. Given the local regression on estimated local space, we provide a novel two-step optimization process for selecting bandwidths of features locally in a data-driven way. Local weighted regression is then applied using the computed bandwidths to produce a smooth image reconstruction with well-preserved details. We derive an error analysis to guide our adaptive sampling process at the local space. We demonstrate that our method produces more accurate and visually pleasing results over the state-of-the-art techniques across a wide range of rendering effects. Our method also allows users to employ an arbitrary set of features, including noisy features, and robustly computes a subset of them by ignoring noisy features and decorrelating them for higher quality.
a) Ours 115 spp (660 s) rMSE 0.00448 (b) LD 128 spp (665 s) rMSE 0.06288 (c) NLM 115 spp (665 s) rMSE 0.01242 (d) SURE 113 spp (665 s) rMSE 0.01521 (e) Ours 115 spp (660 s) rMSE 0.00448 (f) Reference 16K spp Figure 1: Equal-time comparisons in the San Miguel scene. Our method not only produces numerically better, but also visually pleasing results on both focused (top row) and defocused regions (bottom row) compared to non-local means (NLM) [Rousselle et al. 2012] and Stein's unbiased risk estimator based adaptive rendering (SURE) [Li et al. 2012]. As a numerical measure, we use the relative MSE (rMSE) that gives more penalty on dark regions [Rousselle et al. 2012]. Model courtesy of Guillermo M. Leal Llaguno.
Figure 1: Left: Our foveated resolution method running on a commercial video game engine. Right: Our foveated resolution, ambient occlusion, tessellation, and ray-casting (respectively) methods. Areas outwith the circles are the peripheral regions rendered in lower detail.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.