forked from BachiLi/redner
-
Notifications
You must be signed in to change notification settings - Fork 0
Home
Tzu-Mao Li edited this page Feb 3, 2019
·
15 revisions
Redner is a differentiable physically-based Monte Carlo renderer. It takes a 3D scene, including geometry, materials, camera, light sources, represented by PyTorch tensors, and outputs an image, also represented as a PyTorch tensor. It provides necessary machinery for propagating the gradients of the output image to the scene parameters. For the theory behind redner, please consult our paper "Differentiable Monte Carlo Ray Tracing through Edge Sampling". This page is a tutorial for using redner. It is still work in progress. Please let us know what to improve, either through email (tzumao@mit.edu) or Github issues.