Zero-shot 3D shape understanding aims to recognize “unseen” 3D categories that are not
present in training data. Recently, Contrastive Language–Image Pre-training (CLIP) has …

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 …

Reconstructing the shape and spatially varying surface appearances of a physical-world
object as well as its surrounding illumination based on 2D images (eg, photographs) of the …

Inverse path tracing has recently been applied to joint material and lighting estimation, given
geometry and multi-view HDR observations of an indoor scene. However, it has two major …

Computing the gradients of a rendering process is paramount for diverse applications in
computer vision and graphics. However, accurate computation of these gradients is …

High-fidelity 3D assets with materials composed of fibers (including hair), complex layered
material shaders, or fine scattering geometry are critical in high-end realistic rendering …

Discontinuous visibility changes at object boundaries remain a persistent source of difficulty
in the area of differentiable rendering. Left untreated, they bias computed gradients so …

Current differentiable renderers provide light transport gradients with respect to arbitrary
scene parameters. However, the mere existence of these gradients does not guarantee …

Decomposing an object's appearance into representations of its materials and the
surrounding illumination is difficult even when the object's 3D shape is known beforehand …

Physics-based differentiable rendering is becoming increasingly crucial for tasks in inverse
rendering and machine learning pipelines. To address discontinuities caused by geometric …