.png){kind=icon}
返回
Antithetic Sampling for Monte Carlo Differentiable Rendering
.png){kind=icon}
OA
AI
DOI：10.1145/3450626.3459783.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Stochastic sampling of light transport paths is key to Monte Carlo forward rendering, and previous studies have led to mature techniques capable of drawing high-contribution light paths in complex scenes. These sampling techniques have also been applied to differentiable rendering. In this paper, we demonstrate that path sampling techniques developed for forward rendering can become inefficient for differentiable rendering of glossy materials-especially when estimating derivatives with respect to global scene geometries. To address this problem, we introduce antithetic sampling of BSDFs and light-transport paths, allowing significantly faster convergence and can be easily integrated into existing differentiable rendering pipelines. We validate our method by comparing our derivative estimates to those generated with existing unbiased techniques. Further, we demonstrate the effectiveness of our technique by providing equal-quality and equal-time comparisons with existing sampling methods.
Keyword:
Differentiable rendering
antithetic sampling
glossy materials
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.5
论文数:
4.7K
被引数:
3.6W
机构
引用论文
.png){kind=icon}
Motion-compensated frame rate up-conversion based on block matching algorithm with multi-size blocksOAAI
OAAI分享收藏
查看更多内容