3d Reconstruction GitHub Repositories

Instant neural graphics primitives: lightning fast NeRF and more

Node-based Visual Programming Toolbox

A collaboration friendly studio for NeRFs

A resource repository for 3D machine learning

open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.

The open source mesh processing system

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry

A curated list of papers & resources linked to 3D reconstruction from images.

A list of papers and datasets about point cloud analysis (processing)

open Multi-View Stereo reconstruction library

Open source Structure-from-Motion pipeline

A procedural Blender pipeline for photorealistic training image generation

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

3D Computer Vision Framework

pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.

NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

[NeurIPS 2025] PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package

Ray tracing and hybrid rasterization of Gaussian particles

Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes

A fast and robust point cloud registration library

No repository description provided.

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

A Unified Framework for Surface Reconstruction

Index repo for Kimera code

🌍 WorldGen - Generate Any 3D Scene in Seconds

🔥PCL（Point Cloud Library）点云库学习记录