This paper tackles the problem of creating relightable and animatable neural avatars from
sparse-view (or monocular) videos of dynamic humans under unknown illumination …

Abstract Implicit Neural Spatial Representation (INSR) has emerged as an effective
representation of spatially-dependent vector fields. This work explores solving time …

Grid-free Monte Carlo methods based on the walk on spheres (WoS) algorithm solve
fundamental partial differential equations (PDEs) like the Poisson equation without …

Signed distance fields (SDFs) are a widely used implicit surface representation, with broad
applications in computer graphics, computer vision, and applied mathematics. To …

We introduce a Monte Carlo method for computing derivatives of the solution to a partial
differential equation (PDE) with respect to problem parameters (such as domain geometry or …

This paper presents a practical and general approach for computing barycentric coordinates
through stochastic sampling. Our key insight is a reformulation of the kernel integral defining …

𝑌− 1 1 (𝑥, 𝑦, 𝑧)≥ 0.488603 𝑌0 1 (𝑥, 𝑦, 𝑧)≥ 0.690988 𝑌1 1 (𝑥, 𝑦, 𝑧)≥ 0.488603 𝑌− 2 2
(𝑥, 𝑦, 𝑧)≥ 0.546274 𝑌− 1 2 (𝑥, 𝑦, 𝑧)≥ 0.546274 𝑌0 2 (𝑥, 𝑦, 𝑧)≥ 0.446031 𝑌1 2 (𝑥, 𝑦 …

We explore the generalization of the implicit representation in the physical simulation task.
Traditional time-dependent partial differential equations (PDEs) solvers for physical …

Abstract Implicit Neural Representations are powerful tools for representing 3D shapes.
They encode an implicit field in the parameters of a Neural Network, leveraging the power of …

Neural implicit surfaces have emerged as an effective, learnable representation for shapes
of arbitrary topology. However, representing open surfaces remains a challenge. Different …