Antithetic Sampling for Monte Carlo Differentiable Rendering
Zhang, Cheng ; Dong, Zhao ; Doggett, Michael LU
and Zhao, Shuang
(2021)
In ACM Transactions on Graphics
40(4).
p.1-1
- Abstract
- 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... (More) - 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. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/651c97cc-4f98-4ab7-ae99-f7c628ead9fb
- author
- Zhang, Cheng
; Dong, Zhao
; Doggett, Michael
LU
and Zhao, Shuang
- organization
- publishing date
- 2021-07-19
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Computer Graphics, Path Tracing
- in
- ACM Transactions on Graphics
- volume
- 40
- issue
- 4
- article number
- 77
- pages
- 12 pages
- publisher
- Association for Computing Machinery (ACM)
- external identifiers
-
- scopus:85111268442
- ISSN
- 0730-0301
- DOI
- 10.1145/3450626.3459783
- language
- English
- LU publication?
- yes
- id
- 651c97cc-4f98-4ab7-ae99-f7c628ead9fb
- date added to LUP
- 2021-08-27 14:28:47
- date last changed
- 2022-05-12 21:36:30
@article{651c97cc-4f98-4ab7-ae99-f7c628ead9fb,
abstract = {{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.<br/><br/>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.}},
author = {{Zhang, Cheng and Dong, Zhao and Doggett, Michael and Zhao, Shuang}},
issn = {{0730-0301}},
keywords = {{Computer Graphics; Path Tracing}},
language = {{eng}},
month = {{07}},
number = {{4}},
pages = {{1--1}},
publisher = {{Association for Computing Machinery (ACM)}},
series = {{ACM Transactions on Graphics}},
title = {{Antithetic Sampling for Monte Carlo Differentiable Rendering}},
url = {{http://dx.doi.org/10.1145/3450626.3459783}},
doi = {{10.1145/3450626.3459783}},
volume = {{40}},
year = {{2021}},
}