Dr.Jit: A Just-In-Time Compiler for Differentiable Rendering

02/02/2022
by   Wenzel Jakob, et al.
0

Dr.Jit is a new just-in-time compiler for physically based rendering and its derivative. Dr.Jit expedites research on these topics in two ways: first, it traces high-level simulation code (e.g., written in Python) and aggressively simplifies and specializes the resulting program representation, producing data-parallel kernels with state-of-the-art performance on CPUs and GPUs. Second, it simplifies the development of differentiable rendering algorithms. Efficient methods in this area turn the derivative of a simulation into a simulation of the derivative. Dr.Jit provides fine-grained control over the process of automatic differentiation to help with this transformation. Specialization is particularly helpful in the context of differentiation, since large parts of the simulation ultimately do not influence the computed gradients. Dr.Jit tracks data dependencies globally to find and remove redundant computation.

READ FULL TEXT

page 1

page 7

page 10

page 11

page 15

page 17

page 18

page 19

research
04/04/2022

Dressi: A Hardware-Agnostic Differentiable Renderer with Reactive Shader Packing and Soft Rasterization

Differentiable rendering (DR) enables various computer graphics and comp...
research
08/17/2023

Dr.Bokeh: DiffeRentiable Occlusion-aware Bokeh Rendering

Bokeh is widely used in photography to draw attention to the subject whi...
research
06/25/2018

Traffic Differentiation in Dense WLANs with CSMA/ECA-DR MAC Protocol

In today's WLANs, scheduling of packet transmissions solely relies on th...
research
12/03/2021

Differentiable Scripting

In Computational Science, Engineering and Finance (CSEF) scripts typical...
research
07/12/2023

Integrating Enzyme-generated functions into CoDiPack

In operator overloading algorithmic differentiation, it can be beneficia...
research
12/15/2020

AsyncTaichi: Whole-Program Optimizations for Megakernel Sparse Computation and Differentiable Programming

We present a whole-program optimization framework for the Taichi program...
research
03/06/2023

DR-Label: Improving GNN Models for Catalysis Systems by Label Deconstruction and Reconstruction

Attaining the equilibrium state of a catalyst-adsorbate system is key to...

Please sign up or login with your details

Forgot password? Click here to reset