[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

A Unified Framework for Surface Reconstruction

A Modular Framework for 3D Gaussian Splatting and Beyond

Multi-View Environment

[ECCV'20] Convolutional Occupancy Networks

[SIGGRAPH Asia'24 & TOG] Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes

Polygonal Surface Reconstruction from Point Clouds

ManifoldPlus: A Robust and Scalable Watertight Manifold Surface Generation Method for Triangle Soups

[NeurIPS'21] Shape As Points: A Differentiable Poisson Solver

CityGaussian Series for High-quality Large-Scale Scene Reconstruction with Gaussians

[NeurIPS'22] MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction

[TVCG2024] PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction

Learning Implicit Surfaces from Point Clouds (ECCV 2020)

A command line tool to transform a DICOM volume into a 3d surface mesh (obj, stl or ply). Several mesh processing routines can be enabled, such as mesh reduction, smoothing or cleaning. Works on Linux, OSX and Windows.

Intrinsic3D - High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting (ICCV 2017)

Poisson Surface Reconstruction for LiDAR Odometry and Mapping

Massively Parallel Multiview Stereopsis by Surface Normal Diffusion

Volume rendering based surface reconstruction using Unsigned Distance Fields

scikit-fmm is a Python extension module which implements the fast marching method.