1
Geometric Transformer for Fast and Robust Point Cloud Registration
2
Lepard: Learning partial point cloud matching in rigid and deformable scenes
3
End-to-end Learning the Partial Permutation Matrix for Robust 3D Point Cloud Registration
4
CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration
5
PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds
6
Deep Hough Voting for Robust Global Registration
7
You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors
8
HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration
9
FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration
10
4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface
11
LoFTR: Detector-Free Local Feature Matching with Transformers
12
PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency
13
Robust Point Cloud Registration Framework Based on Deep Graph Matching
14
OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration
15
Patch2Pix: Epipolar-Guided Pixel-Level Correspondences
16
PREDATOR: Registration of 3D Point Clouds with Low Overlap
17
SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
19
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
20
DeepGMR: Learning Latent Gaussian Mixture Models for Registration
21
Feature-Metric Registration: A Fast Semi-Supervised Approach for Robust Point Cloud Registration Without Correspondences
22
Deep Global Registration
23
Quasi-Newton Solver for Robust Non-Rigid Registration
24
RPM-Net: Robust Point Matching Using Learned Features
25
D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
26
Circle Loss: A Unified Perspective of Pair Similarity Optimization
27
TEASER: Fast and Certifiable Point Cloud Registration
28
PyTorch: An Imperative Style, High-Performance Deep Learning Library
29
SuperGlue: Learning Feature Matching With Graph Neural Networks
30
PRNet: Self-Supervised Learning for Partial-to-Partial Registration
31
Iterative Distance-Aware Similarity Matrix Convolution with Mutual-Supervised Point Elimination for Efficient Point Cloud Registration
32
Fully Convolutional Geometric Features
33
Deep Closest Point: Learning Representations for Point Cloud Registration
34
KPConv: Flexible and Deformable Convolution for Point Clouds
35
Modeling Point Clouds With Self-Attention and Gumbel Subset Sampling
36
3DRegNet: A Deep Neural Network for 3D Point Registration
37
PointNetLK: Robust & Efficient Point Cloud Registration Using PointNet
38
The Perfect Match: 3D Point Cloud Matching With Smoothed Densities
39
Neighbourhood Consensus Networks
40
PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors
41
3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration
42
SO-Net: Self-Organizing Network for Point Cloud Analysis
43
PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
44
Open3D: A Modern Library for 3D Data Processing
45
Attention is All you Need
46
Using 2 point+normal sets for fast registration of point clouds with small overlap
47
Feature Pyramid Networks for Object Detection
48
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
49
Fast Global Registration
50
3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
51
Robust reconstruction of indoor scenes
52
Adam: A Method for Stochastic Optimization
53
A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM
54
3D ShapeNets: A deep representation for volumetric shapes
55
Are we ready for autonomous driving? The KITTI vision benchmark suite
56
G2o: A general framework for graph optimization
57
Model globally, match locally: Efficient and robust 3D object recognition
58
Fast Point Feature Histograms (FPFH) for 3D registration
59
Global Correspondence Optimization for Non‐Rigid Registration of Depth Scans
60
A spectral technique for correspondence problems using pairwise constraints
61
Method for registration of 3-D shapes
62
A Method for Registration of 3-D Shapes
63
Concerning nonnegative matrices and doubly stochastic matrices
64
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
65
2) weighted cross-entropy loss 83
66
feature learning, 3D modeling, 3D object recognition, and scene understanding
