Abstract The task of Visual Place Recognition (VPR) aims to match a query image against
references from an extensive database of images from different places relying solely on …

This paper presents a novel neural implicit radiance representation for free viewpoint
relighting from a small set of unstructured photographs of an object lit by a moving point light …

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 …

Optimal transport is a long‐standing theory that has been studied in depth from both
theoretical and numerical point of views. Starting from the 50s this theory has also found a …

Novel view synthesis from a sparse set of input images is a challenging problem of great
practical interest, especially when camera poses are absent or inaccurate. Direct …

Data augmentation has contributed to the rapid advancement of unsupervised learning on
3D point clouds. However, we argue that data augmentation is not ideal, as it requires a …

We propose NEMTO, the first end-to-end neural rendering pipeline to model 3D transparent
objects with complex geometry and unknown indices of refraction. Commonly used …

Material appearance is a key component of photorealism with a pronounced impact on
human perception. Although there are many prior works targeting at measuring opaque …

We propose a set of techniques to efficiently importance sample the derivatives of a wide
range of Bidirectional Reflectance Distribution Function (BRDF) models. In differentiable …

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