#3d-reconstruction Repositories
Discover 203 active open source GitHub repositories tagged with #3d-reconstruction, accumulating 365,694 total stars (averaging 1,801 stars per project). Leading this topic is NVlabs/instant-ngp with 17,606 stars.
203 repositories total
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities
open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.
A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the model.
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.
[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
Cross-vendor 3D Gaussian Splatting trainer - video to splat to mesh, Vulkan or CUDA.
[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
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 objectโs position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following cat
The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."
An open-source, low-cost DIY 360ยฐ LiDAR scanner and panoramic 3D reconstruction system.
SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
A Fast and Tightly-coupled Sparse-Direct LiDAR-Inertial-Visual Odometry (LIVO).
Frequently Asked Questions
What is the most popular #3d-reconstruction repository on GitHub?
The top ranked open source #3d-reconstruction project on GitHub is NVlabs/instant-ngp with 17,606 stars. Instant neural graphics primitives: lightning fast NeRF and more
Which programming languages are most used in #3d-reconstruction repositories?
Among the top ranked #3d-reconstruction projects on GitHub, the most common programming languages are Python, C++, Jupyter Notebook, Cuda.
How is the #3d-reconstruction repository ranking calculated?
We track 203 active open source repositories tagged with #3d-reconstruction (500+ stars), totaling 365,694 stars with an average of 1,801 stars per repository. Rankings update daily from the GitHub API.