Differentiable Monte Carlo Ray Tracing Through Edge Sampling
Research output: Contribution to journal › Article
- MIT CSAIL
We introduce a general-purpose differentiable ray tracer, which, to our knowledge, is the first comprehensive solution that is able to compute derivatives of scalar functions over a rendered image with respect to arbitrary scene parameters such as camera pose, scene geometry, materials, and lighting parameters. The key to our method is a novel edge sampling algorithm that directly samples the Dirac delta functions introduced by the derivatives of the discontinuous integrand. We also develop efficient importance sampling methods based on spatial hierarchies. Our method can generate gradients in times running from seconds to minutes depending on scene complexity and desired precision.
We interface our differentiable ray tracer with the deep learning library PyTorch and show prototype applications in inverse rendering and the generation of adversarial examples for neural networks.
|Journal||ACM Transactions on Graphics|
|Publication status||Published - 2018|
|MoE publication type||A1 Journal article-refereed|
|Event||ACM International Conference and Exhibition on Computer Graphics and Interactive Techniques|
- Tokyo, Japan
Duration: 4 Dec 2018 → 7 Dec 2018
Conference number: 11
- computer graphics, inverse rendering, ray tracing