Learning to Cluster for Rendering with Many Lights
Name
3478513.3480561.pdf
Size
8.93 MB
Format
Adobe PDF
Checksum (MD5)
38d870099fc5a46bfe53c0f840afb310
Author(s)
Wang, Yu-Chen
Wu, Yu-Ting
Li, Tzu-Mao
Chuang, Yung-Yu
Date Issued
December 10, 2021
Journal
ACM Transactions on Graphics
Publisher
Association for Computing Machinery
Citation
Yu-Chen Wang, Yu-Ting Wu, Tzu-Mao Li, and Yung-Yu Chuang. 2021. Learning to cluster for rendering with many lights. ACM Trans. Graph. 40, 6, Article 277 (December 2021), 10 pages.
Version
Final published version
Abstract
We present an unbiased online Monte Carlo method for rendering with many lights. Our method adapts both the hierarchical light clustering and the sampling distribution to our collected samples. Designing such a method requires us to make clustering decisions under noisy observation, and making sure that the sampling distribution adapts to our target. Our method is based on two key ideas: a coarse-to-fine clustering scheme that can find good clustering configurations even with noisy samples, and a discrete stochastic successive approximation method that starts from a prior distribution and provably converges to a target distribution. We compare to other state-of-the-art light sampling methods, and show better results both numerically and visually.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3478513.3480561
