HomeResearch-feedChannelRankingsGCTTHU AI TROpen DataMust Reading
HomePoint Cloud Registration
Point Cloud Registration是指，为得到被测物体的完整数据模型,需确定一个合适的坐标变换，将从各个视角得到的点集合并到一个统一的坐标系下,形成一个完整的数据点云，以方便地进行可视化等操作。
Year#CitationLike
TEASER: Fast and Certifiable Point Cloud Registration
Yang Heng,Shi Jingnan,Carlone Luca
IEEE Transactions on Robotics, pp.1-20, (2020)
Methods
Conclusion
We propose the first fast and certifiable algorithm for the registration of two sets of 3D points in the presence of large amounts of outlier correspondences
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by19BibtexViews14Links
0
0
Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection
Heng Yang, Pasquale Antonante,Vasileios Tzoumas,Luca Carlone
IEEE Robotics Autom. Lett., no. 2 (2020): 1127-1134
Methods
Conclusion
The approach allows extending the applicability of Black-Rangarajan duality and Graduated Non-convexity to several spatial perception problems, ranging from mesh registration and shape alignment to pose graph optimization
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by8BibtexViews21Links
0
0
3DRegNet: A Deep Neural Network for 3D Point Registration
G. Dias Pais,Srikumar Ramalingam,Venu Madhav Govindu,Jacinto C. Nascimento,Rama Chellappa,Pedro Miraldo
CVPR, pp.7191-7201, (2020)
Methods
Conclusion
We propose 3DRegNet, a deep neural network that can solve the scan registration problem by jointly solving the outlier rejection given 3D point correspondences and computing the pose for alignment of the scans
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by6BibtexViews43Links
0
0
One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers
Yang Heng,Carlone Luca
NIPS 2020, (2020)
Methods
Conclusion
We have proposed a general framework for designing certifiable algorithms for a broad class of robust geometric perception problems
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by2BibtexViews15Links
0
0
Learning multiview 3D point cloud registration
Gojcic Zan,Zhou Caifa,Wegner Jan D.,Guibas Leonidas J.,Birdal Tolga
CVPR, pp.1756-1766, (2020)
Methods
Conclusion
Research on local descriptors for pairwise registration of 3D point clouds is centered on deep learning approaches that succeed in capturing and encoding evidence hidden to hand-engineered descriptors
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by2BibtexViews70Links
0
0
PointGMM: A Neural GMM Network for Point Clouds
Amir Hertz,Rana Hanocka,Raja Giryes,Daniel Cohen-Or
CVPR, pp.12051-12060, (2020)
Methods
Conclusion
We have introduced a novel framework to transform point clouds into a hierarchical Gaussian mixture model representation
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by1BibtexViews44Links
0
0
ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning
Weiwei Sun,Wei Jiang,Eduard Trulls,Andrea Tagliasacchi,Kwang Moo Yi
CVPR, pp.11283-11292, (2020)
Methods
Conclusion
We have proposed Attentive Context Normalization, and used it to build Attentive Context Networks to solve problems on permutation-equivariant data
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by1BibtexViews34Links
0
0
D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
Bai Xuyang,Luo Zixin,Zhou Lei,Fu Hongbo,Quan Long,Tai Chiew-Lan
CVPR, pp.6358-6366, (2020)
Methods
Conclusion
The registration is considered accurate if the Relative Translation Error is below 2m and Relative Rotation Error is below 5◦ following
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by1BibtexViews32Links
0
0
Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences
Xiaoshui Huang,Guofeng Mei,Jian Zhang
CVPR, pp.11363-11371, (2020)
Methods
Conclusion
We propose a feature-metric framework to solve the point cloud registration, and the framework can be trained using a semi-supervised or unsupervised manner
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by0BibtexViews37Links
0
0
End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
Li Lei,Zhu Siyu,Fu Hongbo,Tan Ping,Tai Chiew-Lan
CVPR, pp.1916-1925, (2020)
Methods
Conclusion
We have presented a novel end-to-end framework for learning local multi-view descriptors of 3D point clouds
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by0BibtexViews46Links
0
0
PREDATOR: Registration of 3D Point Clouds with Low Overlap
Shengyu Huang,Zan Gojcic, Mikhail Usvyatsov, Andreas Wieser,Konrad Schindler
Methods
Conclusion
The core of the model is an overlap attention module that enables early information exchange between the point clouds’ latent encodings, in order to infer which of their points are likely to lie in their overlap region
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by0BibtexViews7Links
0
0
SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
Sheng Ao,Qingyong Hu,Bo Yang,Andrew Markham,Yulan Guo
Extracting robust and general 3D local features is key to downstream tasks such as point cloud registration and reconstruction. Existing learning-based local descriptors are either sensitive to rotation transformations, or rely on classical handcrafted features which are neithe...
default
Comments
Weibo
Cited by0BibtexViews5Links
0
0
CLIPPER: A Graph-Theoretic Framework for Robust Data Association
Parker C. Lusk,Kaveh Fathian,Jonathan P. How
Methods
Conclusion
We presented CLIPPER, a graph-theoretic framework for robust data association using the notion of geometric consistency
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by0BibtexViews4Links
0
0
ROBIN: a Graph-Theoretic Approach to Reject Outliers in Robust Estimation using Invariants
Jingnan Shi, Heng Yang,Luca Carlone
Methods
Conclusion
This paper develops an approach to prune outliers
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by0BibtexViews7Links
0
0
Registration Loss Learning for Deep Probabilistic Point Set Registration
Felix Järemo Lawin, Per-Erik Forssén
Methods
Conclusion
We have extended the paradigm of probabilistic point set registration to exploit the discriminative powers of learned features and weights
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by0BibtexViews2Links
0
0
MaskNet: A Fully-Convolutional Network to Estimate Inlier Points
Vinit Sarode, Animesh Dhagat,Rangaprasad Arun Srivatsan, Nicolas Zevallos,Simon Lucey,Howie Choset
Methods
Conclusion
That MaskNet – augments the ability of existing classical and deep learning-based registration methods to better deal with partial point clouds and outliers, can be used to reject noise, and generalizes to object categories that it was not trained on
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by0BibtexViews8Links
0
0
Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations
Sk Aziz Ali, Kerem Kahraman,Christian Theobalt,Didier Stricker,Vladislav Golyanik
Methods
Conclusion
While most competing methods get trapped in the local minima caused by non-uniform point sampling, our Fast Gravitational Approach recovers transformations which are closer to the optimal ones, thanks to the boundary conditions defined on masses via the Smooth-Particle Mass funct...
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by0BibtexViews11Links
0
0
Distinctive 3D local deep descriptors
Fabio Poiesi, Davide Boscaini
Methods
Conclusion
We presented a novel approach to learn local, compact and rotation invariant descriptors end-to-end through a PointNetbased deep neural network using canonicalised patches
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by0BibtexViews8Links
0
0
DeepGMR: Learning Latent Gaussian Mixture Models for Registration
Wentao Yuan,Ben Eckart,Kihwan Kim,Varun Jampani,Dieter Fox,Jan Kautz
european conference on computer vision, pp.733-750, (2020)
Conclusion
We have proposed Deep Gaussian Mixture Registration, a first attempt towards learning-based probabilistic registration
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by0BibtexViews20Links
0
0
3D Correspondence Grouping with Compatibility Features
Jiaqi Yang, Jiahao Chen, Zhiqiang Huang, Siwen Quan,Yanning Zhang,Zhiguo Cao
Methods
Conclusion
We find that the pipeline of our proposed compatibility feature-based 3D correspondence grouping method can be generalized to matching problems for many other data representations, such as 2D images and non-rigid point clouds/meshes, which remains an interesting future research d...
Must ReadingMust ReadingMust Reading
Comments
Weibo
Cited by0BibtexViews37Links
0
0
Keywords
Computer VisionGraph MatchingImage MatchingImage RegistrationMachine LearningComputational ComplexityConvergenceData MiningFeature ExtractionOptimization
Authors
Birdal Tolga
Birdal Tolga
Paper 5
Luca Carlone
Luca Carlone
Paper 5
Heng(Hank) Yang
Heng(Hank) Yang
Paper 5
Jiaqi Yang
Jiaqi Yang
Paper 4
Federico Tombari
Federico Tombari
Paper 3
Samuele Salti
Samuele Salti
Paper 3
Slobodan Ilic
Slobodan Ilic
Paper 3
Didier Stricker
Didier Stricker
Paper 3
Vladlen Koltun
Vladlen Koltun
Paper 3
Yanning Zhang
Yanning Zhang
Paper 3
IJCAI 2020cvpr2020Papers, Authors, Comments