Affiliation:
1. University of California, Irvine, USA
2. MIT CSAIL, USA
3. University of California, San Diego, USA
Abstract
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.
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Graphics and Computer-Aided Design
Reference28 articles.
1. Dejan Azinović Tzu-Mao Li Anton Kaplanyan and Matthias Nießner. 2019. Inverse Path Tracing for Joint Material and Lighting Estimation. In Computer Vision and Pattern Recognition. Dejan Azinović Tzu-Mao Li Anton Kaplanyan and Matthias Nießner. 2019. Inverse Path Tracing for Joint Material and Lighting Estimation. In Computer Vision and Pattern Recognition.
2. Differentiable Rendering of Neural SDFs through Reparameterization
3. Unbiased warped-area sampling for differentiable rendering
4. Subrahmanyan Chandrasekhar . 1960. Radiative transfer . Courier Corporation . Subrahmanyan Chandrasekhar. 1960. Radiative transfer. Courier Corporation.
5. Chengqian Che , Fujun Luan , Shuang Zhao , Kavita Bala , and Ioannis Gkioulekas . 2020 . Towards Learning-based Inverse Subsurface Scattering. In 2020 IEEE International Conference on Computational Photography (ICCP). IEEE, 1--12 . Chengqian Che, Fujun Luan, Shuang Zhao, Kavita Bala, and Ioannis Gkioulekas. 2020. Towards Learning-based Inverse Subsurface Scattering. In 2020 IEEE International Conference on Computational Photography (ICCP). IEEE, 1--12.