.png){kind=icon}
返回
Learning to Cluster for Rendering with Many Lights
.png){kind=icon}
OA
AI
DOI：10.1145/3478513.3480561.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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-ofthe-art light sampling methods, and show better results both numerically and visually.
Keyword:
Direct illumination
ray tracing
many-light rendering
optimization theory
reinforcement learning
期刊
IF:
9.5
论文数:
4.7K
被引数:
3.6W
机构
引用论文
Remodeling of Neuromuscular Junctions in Target Muscle Following Nerve Regeneration in Mice After Delayed Peripheral Nerve Repair.png)
Neuroscience
OAAI
NeuroscienceIF0
OAAI分享收藏
查看更多内容