Warped-Area Reparameterization of Differential Path Integrals

Warped-Area Reparameterization of Differential Path Integrals
复制标题

微分路径积分的扭曲面积重新参数化

DOI:
10.1145/3618330
复制
发表时间:
2023
影响因子:
6.2
通讯作者:
Zhao, Shuang
Zhao, Shuang
中科院分区:
计算机科学1区
文献类型:
--
作者:
Xu, Peiyu;Bangaru, Sai;Li, Tzu-Mao;Zhao, Shuang

文献摘要

参考文献

被引文献

相似文献

基于物理的可微分渲染在逆渲染和机器学习管道任务中变得越来越重要。为了解决由几何边界和遮挡引起的不连续问题,提出了两类方法:1)直接在场景不连续边界处对光路进行采样的边缘采样方法,该方法需要非平凡的数据结构和预先计算来选择边缘;2)避免不连续采样的再参数化方法,但目前仅限于半球面积分和单向路径跟踪。我们引入了一个新的数学公式,它享有这两类方法的好处。与以往着重于半球积分的再参数化工作不同,我们推导了路径空间中的再参数化。因此,为了使用我们的公式估计导数,我们可以应用高级蒙特卡罗渲染方法,如双向路径跟踪,同时避免对不连续边界进行显式采样。我们给出了可微渲染和逆渲染的结果来证明我们方法的有效性。
Physics-based differentiable rendering is becoming increasingly crucial for tasks in inverse rendering and machine learning pipelines. To address discontinuities caused by geometric boundaries and occlusion, two classes of methods have been proposed: 1) the edge-sampling methods that directly sample light paths at the scene discontinuity boundaries, which require nontrivial data structures and precomputation to select the edges, and 2) the reparameterization methods that avoid discontinuity sampling but are currently limited to hemispherical integrals and unidirectional path tracing.We introduce a new mathematical formulation that enjoys the benefits of both classes of methods. Unlike previous reparameterization work that focused on hemispherical integral, we derive the reparameterization in the path space. As a result, to estimate derivatives using our formulation, we can apply advanced Monte Carlo rendering methods, such as bidirectional path tracing, while avoiding explicit sampling of discontinuity boundaries. We show differentiable rendering and inverse rendering results to demonstrate the effectiveness of our method.
DOI: 10.1145/3528223.3530080
发表时间: 2022
影响因子: 6.2
作者:
Yan, Kai;Lassner, Christoph;Budge, Brian;Dong, Zhao;Zhao, Shuang
通讯作者: Zhao, Shuang
用于路径空间可微渲染的像素重建滤波器的高效微分
DOI: 10.1145/3550454.3555500
发表时间: 2022
影响因子: 6.2
作者:
Yu, Zihan;Zhang, Cheng;Nowrouzezahrai, Derek;Dong, Zhao;Zhao, Shuang
通讯作者: Zhao, Shuang
路径重放反向传播
DOI: 10.1145/3476576.3476672
发表时间: 2021
期刊: ACM Transactions on Graphics (TOG)
影响因子: --
作者:
Delio Vicini;Sébastien Speierer;Wenzel Jakob
通讯作者: Wenzel Jakob
蒙特卡罗可微分渲染的对偶采样
DOI: 10.1145/3450626.3459783
发表时间: 2021
影响因子: 6.2
作者:
Zhang, Cheng;Dong, Zhao;Doggett, Michael;Zhao, Shuang
通讯作者: Zhao, Shuang
通过重新参数化进行神经 SDF 的可微渲染
DOI: 10.1145/3550469.3555397
发表时间: 2022
影响因子: 6.2
作者:
Bangaru, Sai Praveen;Gharbi, Michael;Luan, Fujun;Li, Tzu-Mao;Sunkavalli, Kalyan;Hasan, Milos;Bi, Sai;Xu, Zexiang;Bernstein, Gilbert;Durand, Fredo
通讯作者: Durand, Fredo