Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
awesome-3D-vision
3D computer vision incuding SLAM，VSALM，Deep Learning，Structured light，Stereo，Three-dimensional reconstruction，Computer vision，Machine Learning and so on
https://github.com/Hardy-Uint/awesome-3D-vision
Last synced: about 24 hours ago
JSON representation
-
相机技术&参数
-
资源
-
优秀开源项目汇总
-
Multi-view Stereo
-
Courses
- Digital & Computational Photography - Fredo Durand (MIT)
- Computational Photography - Alexei A. Efros (CMU)
- Courses in Graphics - Stanford University
- Introduction to Visual Computing - Kyros Kutulakos (University of Toronto)
- Computational Photography - Kyros Kutulakos (University of Toronto)
- Computational Photography - Derek Hoiem (UIUC)
- Image Manipulation and Computational Photography - Alexei A. Efros (UC Berkeley)
- Computational Photography - James Hays (Brown University)
-
Project&code
- GPUIma + fusibile - contamination |
- 多视角立体视觉MVS简介
-
paper
- Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume
- Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
- Point-Based Multi-View Stereo Network
- Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference
- NRMVS: Non-Rigid Multi-View Stereo
- Multi-View Stereo 3D Edge Reconstruction
- Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference
- Multi-view stereo: A tutorial
- State of the Art 3D Reconstruction Techniques - [Large scale MVS](http://www.cse.wustl.edu/~furukawa/papers/cvpr2014_tutorial_large_scale_mvs.pdf)
- Accurate, Dense, and Robust Multiview Stereopsis
- State of the art in high density image matching
- Pixelwise View Selection for Unstructured Multi-View Stereo - M. Frahm. ECCV 2016.
- TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo
- Multi-View Stereo via Graph Cuts on the Dual of an Adaptive Tetrahedral Mesh
- Towards high-resolution large-scale multi-view stereo - H. Vu, P. Labatut, J.-P. Pons, R. Keriven. CVPR 2009.
- Refinement of Surface Mesh for Accurate Multi-View Reconstruction
- Exploiting Visibility Information in Surface Reconstruction to Preserve Weakly Supported Surfaces
- A New Variational Framework for Multiview Surface Reconstruction
- Global, Dense Multiscale Reconstruction for a Billion Points
- Efficient Multi-view Surface Refinement with Adaptive Resolution Control
- Multi-View Inverse Rendering under Arbitrary Illumination and Albedo
- Shading-aware Multi-view Stereo
- Scalable Surface Reconstruction from Point Clouds with Extreme Scale and Density Diversity
- Matchnet: Unifying feature and metric learning for patch-based matching
- Efficient deep learning for stereo matching
- Learning a multi-view stereo machine
- Learned multi-patch similarity
- MVSNet: Depth Inference for Unstructured Multi-view Stereo
- DPSNET: END-TO-END DEEP PLANE SWEEP STEREO - Gon Jeon, Stephen Lin, In So Kweon. 2019.
- Point-based Multi-view Stereo Network
- Seamless image-based texture atlases using multi-band blending - P. Pons and R. Keriven. ICPR 2008.
- 3D Textured Model Encryption via 3D Lu Chaotic Mapping
-
Software
- Peter Kovesi's Matlab Functions for Computer Vision and Image Analysis
- MinimalSolvers - Minimal problems solver
- Multi-View Environment
- Visual SFM
- Bundler SFM
- openMVG: open Multiple View Geometry - Multiple View Geometry; Structure from Motion library & softwares
- Floating Scale Surface Reconstruction
- Large-Scale Texturing of 3D Reconstructions
-
-
Courses
-
Code
- Computer Vision - Derek Hoiem (UIUC)
- EENG 512 / CSCI 512 - Computer Vision - William Hoff (Colorado School of Mines)
- 3D Computer Vision: Past, Present, and Future
- Visual Object and Activity Recognition - Alexei A. Efros and Trevor Darrell (UC Berkeley)
- Language and Vision - Tamara Berg (UNC Chapel Hill)
- Convolutional Neural Networks for Visual Recognition - Fei-Fei Li and Andrej Karpathy (Stanford University)
- Computer Vision: Foundations and Applications - Kalanit Grill-Spector and Fei-Fei Li (Stanford University)
- High-Level Vision: Behaviors, Neurons and Computational Models - Fei-Fei Li (Stanford University)
- Advances in Computer Vision - Antonio Torralba and Bill Freeman (MIT)
- Computer Vision - Bastian Leibe (RWTH Aachen University)
- Computer Vision 2 - Bastian Leibe (RWTH Aachen University)
- Computer Vision
- Computer Vision 1
- Computer Vision 2
- Multiple View Geometry
-
-
视觉SLAM
-
Books
-
Courses&&Lectures
- Geometry and Beyond - Representations, Physics, and Scene Understanding for Robotics
- Robotics - UPenn
- Robot Mapping - UniFreiburg - 2016)
- Robot Mapping - UniBonn
- Introduction to Mobile Robotics - UniFreiburg - 2016)
- Mapping, Localization, and Self-Driving Vehicles
- Robotics - UPenn
- Robust and Efficient Real-time Mapping for Autonomous Robots
- KinectFusion - Real-time 3D Reconstruction and Interaction Using a Moving Depth Camera
-
Code
-
-
Books
-
Code
- Numerical Algorithms: Methods for Computer Vision, Machine Learning, and Graphics - Justin Solomon 2015
- Computer Vision: Models, Learning, and Inference - Simon J. D. Prince 2012
- Computer Vision: Theory and Application - Rick Szeliski 2010
- Visual Object Recognition synthesis lecture - Kristen Grauman and Bastian Leibe 2011
-
-
Github link
-
点云去噪&滤波
-
点云识别&分类
-
点云匹配&配准&对齐&注册
-
商用
- An ICP variant using a point-to-line metric
- Generalized-ICP
- Linear Least-Squares Optimization for Point-to-Plane ICP Surface Registration
- Metric-Based Iterative Closest Point Scan Matching for Sensor Displacement Estimation
- [IROS2018
- [CVPR2019
- [CVPR2019 - Based Randomized Approach for Robust Point Cloud Registration without Correspondences.
- [ICRA2019 - MatchNet: Learning to Match Keypoints across 2D Image and 3D Point Cloud.
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- [IROS2018
- An ICP variant using a point-to-line metric
- [IROS2018
- An ICP variant using a point-to-line metric
- [IROS2018
- An ICP variant using a point-to-line metric
- [IROS2018
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- [IROS2018
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- [CVPR - Set Registration using Gaussian Filter and Twist Parameterization.
- [ICCV2019 - to-End Deep Neural Network for 3D Point Cloud Registration.
- [CVPR2019
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- NICP: Dense Normal Based Point Cloud Registration
- [ICRA2019 - overlap 3-D point cloud registration for outlier rejection.
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
- An ICP variant using a point-to-line metric
-
-
点云数据集
-
商用
- [IQmulus & TerraMobilita Contest
- [ShapeNet
- [PartNet
- [S3DIS - Scale 3D Indoor Spaces Dataset.
- [ScanNet - annotated 3D Reconstructions of Indoor Scenes.
- [Stanford 3D
- [UWA Dataset
- [Princeton Shape Benchmark
- [ASL Datasets Repository(ETH)
- [Ford Campus Vision and Lidar Data Set - 250 pickup truck.
- [The Stanford Track Collection - 64E S2 LIDAR.
- [WAD
- [nuScenes - scale autonomous driving dataset.
- [SynthCity
- [Oxford Robotcar
- [WAD
- [WAD
- [WAD
- [WAD
- [WAD
- [WAD
- [WAD
- [PartNet
- [WAD
- [WAD
- [WAD
- [WAD
- [WAD
- [WAD
- [WAD
- [WAD
- [WAD
- [Large-Scale Point Cloud Classification Benchmark(ETH)
- [Robotic 3D Scan Repository - dimensional laser scans gathered at two unique planetary analogue rover test facilities in Canada.
- [Ford Campus Vision and Lidar Data Set - 250 pickup truck.
- [WAD
- [WAD
- [WAD
- [Oakland 3-D Point Cloud Dataset - D point cloud laser data collected from a moving platform in a urban environment.
- [Robotic 3D Scan Repository
- [WAD
- [PreSIL - wise segmentation (point clouds), ground point labels (point clouds), and detailed annotations for all vehicles and people. [[paper](https://arxiv.org/abs/1905.00160)]
- [PedX - resolution (12MP) stereo images and LiDAR data along with providing 2D and 3D labels of pedestrians. [[ICRA 2019 paper](https://arxiv.org/abs/1809.03605)]
- [Lyft Level 5 - labelled 3D bounding boxes of traffic agents, an underlying HD spatial semantic map.
- [SemanticKITTI
- [WAD
- [WAD
- [WAD
-
-
点云匹配质量评估
-
商用
-
-
点云分割
-
商用
- [CVPR2019 - Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields.
- From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds
- Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation
- JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
- [CVPR2019 - grained and Hierarchical Shape Segmentation.
- [IROS2019
- 基于局部表面凸性的散乱点云分割算法研究
- 三维散乱点云分割技术综述
- 基于聚类方法的点云分割技术的研究
- SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor
- [3DV2017
- [ICRA2017
-
-
点云三维重建
-
商用
- [AAAI2018
- [CVPR2019 - Scale Outdoor Scenes.
- [AAAI2019
- 改进的点云数据三维重建算法
-
-
点云其它
-
单目图像
-
结构光
-
综述
-
Lectures&Video
-
标定
-
Other Papers
- Structured light stereoscopic imaging with dynamic pseudo-random patterns
- Absolute phase mapping for one-shot dense pattern projection
- Absolute phase mapping for one-shot dense pattern projection
- Rapid shape acquisition using color structured light and multi-pass dynamic programming
- Enhanced phase measurement profilometry for industrial 3D inspection automation
- Profilometry of three-dimensional discontinuous solids by combining two-steps temporal phase unwrapping, co-phased profilometry and phase-shifting interferometry
- High-speed 3D image acquisition using coded structured light projection
- Accurate 3D measurement using a Structured Light System
- Robust one-shot 3D scanning using loopy belief propagation
- Robust Segmentation and Decoding of a Grid Pattern for Structured Light
-
Project with code
-
-
立体视觉3D成像
-
双目视觉
- 双目立体视觉匹配技术综述
- DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch
- Improved Stereo Matching with Constant Highway Networks and Reflective Confidence Learning
- Exact Bias Correction and Covariance Estimation for Stereo Vision
- Event-Driven Stereo Matching for Real-Time 3D Panoramic Vision
- Graph Cut based Continuous Stereo Matching using Locally Shared Labels
- Constant Time Weighted Median Filtering for Stereo Matching and Beyond
- A non-local cost aggregation method for stereo matching
- On building an accurate stereo matching system on graphics hardware
- Efficient large-scale stereo matching
- Accurate, dense, and robust multiview stereopsis
- A region based stereo matching algorithm using cooperative optimization
- DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch
- Improved Stereo Matching with Constant Highway Networks and Reflective Confidence Learning
- On building an accurate stereo matching system on graphics hardware
- A constant-space belief propagation algorithm for stereo matching
- Cost aggregation and occlusion handling with WLS in stereo matching
- Efficient minimal-surface regularization of perspective depth maps in variational stereo
- Leveraging Stereo Matching with Learning-based Confidence Measures
- PMSC: PatchMatch-Based Superpixel Cut for Accurate Stereo Matching
- Cross-Scale Cost Aggregation for Stereo Matching
- Fast Cost-Volume Filtering for Visual Correspondence and Beyond
- Stereo matching with color-weighted correlation, hierarchical belief propagation, and occlusion handling
- Stereo matching: An outlier confidence approach
- Multi-view stereo for community photo collections
- A performance study on different cost aggregation approaches used in real-time stereo matching
-
教程
-
综述
-
-
SFM
-
参考
- 基于单目视觉的三维重建算法综述
- Photo Tourism: Exploring Photo Collections in 3D
- Towards linear-time incremental structure from motion
- Structure-from-Motion Revisited
- Global motion estimation from point matches - Nachimson, S. Z. Kovalsky, I. KemelmacherShlizerman, A. Singer, and R. Basri. 3DIMPVT 2012.
- A Global Linear Method for Camera Pose Registration
- Global Structure-from-Motion by Similarity Averaging
- Linear Global Translation Estimation from Feature Tracks
- Structure-and-Motion Pipeline on a Hierarchical Cluster Tree - D Digital Imaging and Modeling, 2009.
- Randomized Structure from Motion Based on Atomic 3D Models from Camera Triplets
- Hierarchical structure-and-motion recovery from uncalibrated images
- Parallel Structure from Motion from Local Increment to Global Averaging
- Robust Structure from Motion in the Presence of Outliers and Missing Data
- Multistage SFM : Revisiting Incremental Structure from Motion - > [Multistage SFM: A Coarse-to-Fine Approach for 3D Reconstruction](http://arxiv.org/abs/1512.06235), arXiv 2016.
- Combining two-view constraints for motion estimation
- Lie-algebraic averaging for globally consistent motion estimation
- Robust rotation and translation estimation in multiview reconstruction
-
Project&code
- MicMac - B |
-
-
TOF
-
Project&code
-
-
Planar Reconstruction
-
3D人脸重建
-
Datasets
- Nonlinear 3D Face Morphable Model
- On Learning 3D Face Morphable Model from In-the-wild Images
- Cascaded Regressor based 3D Face Reconstruction from a Single Arbitrary View Image
- JointFace Alignment and 3D Face Reconstruction
- Photo-Realistic Facial Details Synthesis From Single Image
- FML: Face Model Learning from Videos
- Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric
- Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network
- Joint 3D Face Reconstruction and Dense Face Alignment from A Single Image with 2D-Assisted Self-Supervised Learning
- Photo-Realistic Facial Details Synthesis From Single Image
-
-
纹理/材料分析与合成
-
**场景合成/重建**
-
Datasets
-
-
数据格式不同
-
综述
-
基于图像（2D）
-
基于位置（3D）
-
基于图像和位置（2.5D）
-
深度图补全
- HMS-Net: Hierarchical Multi-scale Sparsity-invariant Network for Sparse Depth Completion
- Sparse and noisy LiDAR completion with RGB guidance and uncertainty
- 3D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalization
- Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion
- Confidence Propagation through CNNs for Guided Sparse Depth Regression
- Learning Guided Convolutional Network for Depth Completion
- DFineNet: Ego-Motion Estimation and Depth Refinement from Sparse, Noisy Depth Input with RGB Guidance
- PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation
- Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints
- Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion
- Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints
- 3D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalization
-
-
相机生产厂家汇总
-
综述
-
单相机标定
- 相机标定误差因素分析
- Fully automatic camera calibration method based on circular markers基于圆形标志点的全自动相机标定方法
- Accurate Feature Extraction and Control Point Correction for Camera Calibration with a Mono-Plane Target
- 基于主动红外辐射标定板的超广角红外相机标定
- 基于相位标靶的相机标定
- 基于广义成像模型的Scheimpflug相机标定方法
- 多几何约束下的鱼眼相机单像高精度标定
- Accurate camera calibration using iterative refinement of control points
-
手眼标定
-
其它
-
-
点云目标检索
-
商用
-
-
点云线、面拟合
Programming Languages
Categories
Multi-view Stereo
50
点云数据集
48
点云匹配&配准&对齐&注册
42
立体视觉3D成像
34
结构光
29
**场景合成/重建**
25
SFM
18
数据格式不同
17
Courses
15
纹理/材料分析与合成
14
点云分割
14
视觉SLAM
13
相机生产厂家汇总
11
3D人脸重建
10
Planar Reconstruction
7
单目图像
6
优秀开源项目汇总
6
点云其它
6
Books
4
点云三维重建
4
点云去噪&滤波
3
点云识别&分类
3
TOF
2
Github link
2
点云目标检索
1
点云匹配质量评估
1
相机技术&参数
1
点云线、面拟合
1
资源
1
Sub Categories
Keywords
slam
3
machine-learning
2
reconstruction
2
point-cloud
2
awesome-list
2
lidar-slam
1
lidar-odometry
1
fusion
1
ros
1
learning
1
computervision
1
books
1
voxel
1
primitives
1
papers
1
neural-networks
1
mesh
1
constructive-solid-geometries
1
3d-reconstruction
1
3d
1
recurrent-networks
1
neural-network
1
face-images
1
deep-networks
1
deep-learning-tutorial
1
deep-learning
1
awesome
1
visual-odometry
1
visual-inertial
1
sfm
1
augmented-reality
1
vslam
1
vins
1
state-estimation
1
semantic
1
research-paper
1
open-source
1
multiple-sensors
1
mobile-robots
1