DiffTaichi: Differentiable Programming for Physical Simulation

1 Oct 2019Yuanming HuLuke AndersonTzu-Mao LiQi SunNathan CarrJonathan Ragan-KelleyFrédo Durand

We present DiffTaichi, a new differentiable programming language tailored for building high-performance differentiable physical simulators. Based on an imperative programming language, DiffTaichi generates gradients of simulation steps using source code transformations that preserve arithmetic intensity and parallelism... (read more)

PDF Abstract

Evaluation Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.