Git Stars Git Stars

#3d-vision Repositories

Discover 28 active open source GitHub repositories tagged with #3d-vision, accumulating 55,835 total stars (averaging 1,994 stars per project). Leading this topic is pengsida/learning_research with 16,077 stars.

28
Total Repositories
55,835
Total Stars
1,994
Avg Stars/Repo
1
pengsida/learning_research

My research experience

pengsida
โญ 16,077 ๐Ÿ‘ค pengsida User ๐Ÿ• Updated 2026-10-14 ๐Ÿ“… Created 2023-05-09
2
realsenseai/realsense-ros

ROS Wrapper for RealSenseโ„ข Cameras

realsenseai
โญ 3,488 Python ๐Ÿ‘ค realsenseai Organization ๐Ÿ• Updated 2026-11-15 ๐Ÿ“… Created 2016-02-23
3
Pointcept/Pointcept

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Utonia (ICML'26), Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

Pointcept
โญ 3,311 Python ๐Ÿ‘ค Pointcept Organization ๐Ÿ• Updated 2026-11-03 ๐Ÿ“… Created 2023-03-21
4
microsoft/MoGe

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

microsoft
โญ 3,171 JavaScript ๐Ÿ‘ค microsoft Organization ๐Ÿ• Updated 2026-11-14 ๐Ÿ“… Created 2024-09-23
5
NVIDIA/MinkowskiEngine

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

NVIDIA
โญ 2,853 Python ๐Ÿ‘ค NVIDIA Organization ๐Ÿ• Updated 2024-03-05 ๐Ÿ“… Created 2019-04-04
6
tensorflow/graphics

TensorFlow Graphics: Differentiable Graphics Layers for TensorFlow

tensorflow
โญ 2,782 Python ๐Ÿ‘ค tensorflow Organization ๐Ÿ• Updated 2026-11-01 ๐Ÿ“… Created 2019-01-08
7
zju3dv/LoFTR

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

zju3dv
โญ 2,765 Jupyter Notebook ๐Ÿ‘ค zju3dv Organization ๐Ÿ• Updated 2024-05-31 ๐Ÿ“… Created 2021-03-02
8
google-research-datasets/Objectron

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 objectโ€™s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following cat

google-research-datasets
โญ 2,361 Jupyter Notebook ๐Ÿ‘ค google-research-datasets Organization ๐Ÿ• Updated 2026-03-06 ๐Ÿ“… Created 2020-10-19
9
junshutang/Make-It-3D

[ICCV 2023] Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior

junshutang
โญ 1,885 Python ๐Ÿ‘ค junshutang User ๐Ÿ• Updated 2024-07-05 ๐Ÿ“… Created 2023-03-23
10
mint-lab/3dv_tutorial

An Invitation to 3D Vision: A Tutorial for Everyone

mint-lab
โญ 1,827 CMake ๐Ÿ‘ค mint-lab Organization ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2017-02-07
11
cvg/pixel-perfect-sfm

Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)

cvg
โญ 1,457 C++ ๐Ÿ‘ค cvg Organization ๐Ÿ• Updated 2024-07-30 ๐Ÿ“… Created 2021-08-17
12
IDEA-Research/awesome-detection-transformer

Collect some papers about transformer for detection and segmentation. Awesome Detection Transformer for Computer Vision (CV)

IDEA-Research
โญ 1,392 ๐Ÿ‘ค IDEA-Research Organization ๐Ÿ• Updated 2024-07-04 ๐Ÿ“… Created 2022-03-09
13
lessthanoptimal/BoofCV

Fast computer vision library for SFM, calibration, fiducials, tracking, image processing, and more.

lessthanoptimal
โญ 1,205 Java ๐Ÿ‘ค lessthanoptimal User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2011-04-19
โญ 1,125 ๐Ÿ‘ค 52CV User ๐Ÿ• Updated 2024-06-27 ๐Ÿ“… Created 2023-11-29
15
guochengqian/PointNeXt

[NeurIPS'22] PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies

guochengqian
โญ 1,094 Python ๐Ÿ‘ค guochengqian User ๐Ÿ• Updated 2026-07-06 ๐Ÿ“… Created 2022-05-21
16
caiyuanhao1998/Open-DiffusionGS

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction (ICCV 2025)

caiyuanhao1998
โญ 871 Python ๐Ÿ‘ค caiyuanhao1998 User ๐Ÿ• Updated 2026-11-14 ๐Ÿ“… Created 2024-11-17
17
DirtyHarryLYL/LLM-in-Vision

Recent LLM-based CV and related works. Welcome to comment/contribute!

DirtyHarryLYL
โญ 868 ๐Ÿ‘ค DirtyHarryLYL User ๐Ÿ• Updated 2025-03-08 ๐Ÿ“… Created 2023-03-10
18
caiyuanhao1998/SAX-NeRF

"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024) - A Toolbox for CT reconstruction and X-ray Novel View Synthesis

caiyuanhao1998
โญ 814 Python ๐Ÿ‘ค caiyuanhao1998 User ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2023-11-17
19
radekd91/emoca

Official repository accompanying a CVPR 2022 paper EMOCA: Emotion Driven Monocular Face Capture And Animation. EMOCA takes a single image of a face as input and produces a 3D reconstruction. EMOCA sets the new standard on reconstructing highly emotional images in-the-wild

radekd91
โญ 813 Python ๐Ÿ‘ค radekd91 User ๐Ÿ• Updated 2024-12-06 ๐Ÿ“… Created 2022-03-10
20
KangLiao929/Awesome-Deep-Camera-Calibration

Deep Learning for Camera Calibration and Beyond: A Survey

KangLiao929
โญ 758 ๐Ÿ‘ค KangLiao929 User ๐Ÿ• Updated 2025-10-30 ๐Ÿ“… Created 2022-05-12
21
qq456cvb
โญ 728 Python ๐Ÿ‘ค qq456cvb User ๐Ÿ• Updated 2026-06-13 ๐Ÿ“… Created 2020-12-22
22
DL3DV-10K/Dataset

News: the 10k dataset is ready for download.

DL3DV-10K
โญ 693 HTML ๐Ÿ‘ค DL3DV-10K Organization ๐Ÿ• Updated 2026-02-10 ๐Ÿ“… Created 2023-12-23
23
InternRobotics/EmbodiedScan

[CVPR 2024 & NeurIPS 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

InternRobotics
โญ 668 Python ๐Ÿ‘ค InternRobotics Organization ๐Ÿ• Updated 2025-06-13 ๐Ÿ“… Created 2023-12-11
24
zju3dv/Diffuman4D

[ICCV 2025] Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models

zju3dv
โญ 646 Python ๐Ÿ‘ค zju3dv Organization ๐Ÿ• Updated 2026-09-15 ๐Ÿ“… Created 2025-03-24
25
Eyeline-Labs/Vista4D

Official code, models, and data for Vista4D: Video Reshooting with 4D Point Clouds (CVPR 2026 Highlight)

Eyeline-Labs
โญ 621 Python ๐Ÿ‘ค Eyeline-Labs Organization ๐Ÿ• Updated 2026-06-02 ๐Ÿ“… Created 2025-11-20
26
zju3dv/manhattan_sdf

Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral

zju3dv
โญ 533 Python ๐Ÿ‘ค zju3dv Organization ๐Ÿ• Updated 2026-09-15 ๐Ÿ“… Created 2022-05-05
27
Inception3D/Easi3R

[ICCV 2025] A simple training-free approach adapting DUSt3R for dynamic scenes.

Inception3D
โญ 529 Python ๐Ÿ‘ค Inception3D Organization ๐Ÿ• Updated 2025-04-01 ๐Ÿ“… Created 2025-03-15
28
alexklwong/awesome-state-of-depth-completion

Current state of supervised and unsupervised depth completion methods

alexklwong
โญ 513 ๐Ÿ‘ค alexklwong User ๐Ÿ• Updated 2025-03-16 ๐Ÿ“… Created 2020-03-10

Frequently Asked Questions

1

What is the most popular #3d-vision repository on GitHub?

The top ranked open source #3d-vision project on GitHub is pengsida/learning_research with 16,077 stars. My research experience

2

Which programming languages are most used in #3d-vision repositories?

Among the top ranked #3d-vision projects on GitHub, the most common programming languages are Python, Jupyter Notebook, JavaScript, CMake.

3

How is the #3d-vision repository ranking calculated?

We track 28 active open source repositories tagged with #3d-vision (500+ stars), totaling 55,835 stars with an average of 1,994 stars per repository. Rankings update daily from the GitHub API.