implicit-surfaces

This repository contains the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"

Multi-view 3D reconstruction using neural rendering. Unofficial implementation of UNISURF, VolSDF, NeuS and more.

blazing fast implicit surface evaluation

PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces (CVPR 2023)

HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details (NeurIPS 2022)

Reference implementation for "Massively Parallel Rendering of Complex Closed-Form Implicit Surfaces" (SIGGRAPH 2020)

Source code for the Computer Graphics Forum paper: Segment Tracing Using Local Lipschitz Bounds. Presented at Eurographics 2020.

[3DV 2024] Color-NeuS: Reconstructing Neural Implicit Surfaces with Color

GPU-accelerated math function graphers in web browsers, both 3D and 2D.

3D/2D CAD design package written in Go. GPU accelerated.

three.js addon for triangulation of implicit surfaces and for forms with holes. The addon generates indexed BufferGeometries.

🧱 World leading open-source geometry engine in context of Implicit Surface Modelling, featuring sharp edges: Library for Geometric / Solid Modelling mesh generation slicing, and more, based on 🪐 Implicit Surfaces modelling. (Feel free to submit Pull Requests)

Reference implementation for "Temporal Set Inversion for Animated Implicits" (SIGGRAPH 2023)

C++ version based on the Marching Cubes library of the paper: http://jcgt.org/published/0008/03/01

Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (CVPR 2025)

Source code for the TOG paper: Terrain Amplification with Implicit 3D Features. Presented at Siggraph Asia 2019.

Source code for our Computer Graphics Forum paper: Synthesizing Geologically Coherent Cave Networks.

Data-Driven 3D Reconstruction of Dressed Humans from Sparse Views

Volumetric and implicit surfaces (SDF) pathtracer implementation built on top of Yocto/GL.

Latest version of the Marching Cubes library described in the paper: http://jcgt.org/published/0008/03/01