Differentiable rendering computes derivatives of the light transport equation with respect to
arbitrary 3D scene parameters, and enables various applications in inverse rendering and …

We present a method to automatically compute correct gradients with respect to geometric
scene parameters in neural SDF renderers. Recent physically-based differentiable …

We introduce vertex block descent, a block coordinate descent solution for the variational
form of implicit Euler through vertex-level Gauss-Seidel iterations. It operates with local …

We propose a novel method to reconstruct the 3D shapes of transparent objects using hand-
held captured images under natural light conditions. It combines the advantage of explicit …

Monte Carlo rendering algorithms often utilize correlations between pixels to improve
efficiency and enhance image quality. For real-time applications in particular, repeated …

We present 3DeepCT, a deep neural network for computed tomography, which performs 3D
reconstruction of scattering volumes from multi-view images. The architecture is dictated by …

The modern realistic computer graphics is based on physically correct lighting simulation.
One of the main and computationally difficult problems is the calculation of light transport or …

The rendering efficiency of Monte Carlo path tracing often depends on the ease of path
construction. For scenes with particularly complex visibility, eg where the camera and light …

High-resolution tactile sensors are very helpful to robots for fine-grained perception and
manipulation tasks, but designing those sensors is challenging. This is because the designs …

Physics-based differentiable rendering requires estimating boundary path integrals
emerging from the shift of discontinuities (eg, visibility boundaries). Previously, although the …