Adaptive Rendering based on Weighted Local Regression

Bochang Moon 1 , Nathan Carr 2 , Sung-Eui Yoon 1

KAIST 1 , Adobe 2

ACM Transactions on Graphics 2014 (Presented at SIGGRAPH 2015)

This figure shows equal-time adaptive rendering results in the San Miguel scene. Our method shows more visually pleasing results on both defocused (the top row) and focused regions (the bottom row), and has numerically better results, about 3:1 reduction ratios on average, over NLM and SURE.


Monte Carlo ray tracing is considered one of the most effective techniques for rendering photo-realistic imagery, but it 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 use 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.

Video (available to download in the last section)