activity
20172022
most citedDr.Jit: A Just-In-Time Compiler for Differentiable Rendering

150 citations · 159 across the 6 of their papers we have counts for

collaborators

6 papers

cs.GR2022★ 1 cited

Solving Inverse PDE Problems using Grid-Free Monte Carlo Estimators

Ekrem Fatih Yılmazer, Delio Vicini, Wenzel Jakob

Modeling physical phenomena like heat transport and diffusion is crucially dependent on the numerical solution of partial differential equations (PDEs). A PDE solver finds the solu…

cs.GR2022★ 150 cited

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

Wenzel Jakob, Sébastien Speierer, Nicolas Roussel +1

DrJit is a new just-in-time compiler for physically based rendering and its derivative. DrJit expedites research on these topics in two ways: first, it traces high-level simu…

cs.CV2021

Wide-Depth-Range 6D Object Pose Estimation in Space

Yinlin Hu, Sebastien Speierer, Wenzel Jakob +2

6D pose estimation in space poses unique challenges that are not commonly encountered in the terrestrial setting. One of the most striking differences is the lack of atmospheric sc…

cs.GR2018

-Method for Multiple Scattering in Participating Media

David Koerner, Jamie Portsmouth, Wenzel Jakob

Rendering highly scattering participating media using brute force path tracing is a challenge. The diffusion approximation reduces the problem to solving a simple linear partial di…

cs.GR2017★ 5 cited

Scratch iridescence: Wave-optical rendering of diffractive surface structure

Sebastian Werner, Zdravko Velinov, Wenzel Jakob +1

The surface of metal, glass and plastic objects is often characterized by microscopic scratches caused by manufacturing and/or wear. A closer look onto such scratches reveals iride…

cs.GR2017★ 3 cited

Reversible Jump Metropolis Light Transport using Inverse Mappings

Benedikt Bitterli, Wenzel Jakob, Jan Novák +1

We study Markov Chain Monte Carlo (MCMC) methods operating in primary sample space and their interactions with multiple sampling techniques. We observe that incorporating the sampl…