This repository contains the full project files, report, poster, and demonstration animations for a self-supervised neural framework that reconstructs 3D surfaces directly from unstructured point ...

This repository contains the Python code to reproduce some of the experiments of the Siggraph 2022 paper "Differentiable Signed Distance Function Rendering". Please see the project page for the paper ...

I will define a new distance function on an unoriented 3D point set and describe how it may be used to reconstruct a surface approximating these points. This distance function is shown to be a ...

Abstract: Distance function is a main metrics of measuring the affinity between two data points in machine learning. Extant distance functions often provide unreachable distance values in real ...