Deep neural networks (DNNs) have shown remarkable performance improvements on
vision-related tasks such as object detection or image segmentation. Despite their success …

We present an efficient method for joint optimization of topology, materials and lighting from
multi-view image observations. Unlike recent multi-view reconstruction approaches, which …

Recent advances in differentiable rendering have enabled high-quality reconstruction of 3D
scenes from multi-view images. Most methods rely on simple rendering algorithms: pre …

Physically-based differentiable rendering has recently emerged as an attractive new
technique for solving inverse problems that recover complete 3D scene representations from …

We propose a neural inverse rendering pipeline called IRON that operates on photometric
images and outputs high-quality 3D content in the format of triangle meshes and material …

Inverse reconstruction from images is a central problem in many scientific and engineering
disciplines. Recent progress on differentiable rendering has led to methods that can …

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 …

We present a method for reducing errors---variance and bias---in physically based
differentiable rendering (PBDR). Typical applications of PBDR repeatedly render a scene as …

Differentiable physically-based rendering has become an indispensable tool for solving
inverse problems involving light. Most applications in this area jointly optimize a large set of …

We consider the challenging problem of predicting intrinsic object properties from a single
image by exploiting differentiable renderers. Many previous learning-based approaches for …