PC-Net: Unsupervised Point Correspondence Learning with Neural Networks

Li, Xiang; Wang, Lingjing; Fang, Yi

doi:10.1109/3dv.2019.00025

Cited by 20 publications

(21 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, learning-based methods have achieved great success in many fields of computer vision [24], [25], [26], [27], [28], [29], [30], [31], [32], [33]. In particular, recent works have started a trend of directly learning geometric features from cloud points (especially 3D points), which motivates us to approach the point set registration problem using deep neural networks [19], [20], [27], [28], [29], [30], [34], [35], [36], [37]. PointNetLK [38] was proposed by Aoki et al to leverage the newly proposed PointNet algorithm for directly extracting features from the point cloud with the classical Lucas & Kanade algorithm for the rigid registration of 3D point sets.…”

Section: Learning-based Registration Methodsmentioning

confidence: 99%

Unsupervised Learning of 3D Point Set Registration

Wang¹,

Li²,

Fang³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Point cloud registration is the process of aligning a pair of point sets via searching for a geometric transformation. Recent works leverage the power of deep learning for registering a pair of point sets. However, unfortunately, deep learning models often require a large number of ground truth labels for training. Moreover, for a pair of source and target point sets, existing deep learning mechanisms require explicitly designed encoders to extract both deep spatial features from unstructured point clouds and their spatial correlation representation, which is further fed to a decoder to regress the desired geometric transformation for point set alignment. To further enhance deep learning models for point set registration, this paper proposes Deep-3DAligner, a novel unsupervised registration framework based on a newly introduced deep Spatial Correlation Representation (SCR) feature. The SCR feature describes the geometric essence of the spatial correlation between source and target point sets in an encoding-free manner. More specifically, our method starts with optimizing a randomly initialized latent SCR feature, which is then decoded to a geometric transformation (i.e., rotation and translation) to align source and target point sets. Our Deep-3DAligner jointly updates the SCR feature and weights of the transformation decoder towards the minimization of an unsupervised alignment loss. We conducted experiments on the Model-Net40 datasets to validate the performance of our unsupervised Deep-3DAligner for point set registration. The results demonstrated that, even without ground truth and any assumption of a direct correspondence between source and target point sets for training, our proposed approach achieved comparative performance compared to most recent supervised state-of-the-art approaches.

show abstract

Section: Learning-based Registration Methodsmentioning

confidence: 99%

Unsupervised Learning of 3D Point Set Registration

Wang¹,

Li²,

Fang³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are some supervised methods (Lu et al 2019;Yuan et al 2020;Sarode et al 2020;Huang et al 2021). PointNetLK (Aoki et al 2019) Additionally, there are some end-to-end unsupervised point cloud registration methods (Kadam et al 2020;Feng et al 2021;Li, Wang, and Fang 2019;El Banani, Gao, and Johnson 2021). (Yang et al 2020;Groueix et al 2019) employ cycle consistency across the pairwise point clouds for points matching, which cannot be trained directly on the partial data.…”

Section: Related Workmentioning

confidence: 99%

Reliable Inlier Evaluation for Unsupervised Point Cloud Registration

Shen¹,

Liu²,

Jiang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Unsupervised point cloud registration algorithm usually suffers from the unsatisfied registration precision in the partially overlapping problem due to the lack of effective inlier evaluation. In this paper, we propose a neighborhood consensus based reliable inlier evaluation method for robust unsupervised point cloud registration. It is expected to capture the discriminative geometric difference between the source neighborhood and the corresponding pseudo target neighborhood for effective inlier distinction. Specifically, our model consists of a matching map refinement module and an inlier evaluation module. In our matching map refinement module, we improve the point-wise matching map estimation by integrating the matching scores of neighbors into it. The aggregated neighborhood information potentially facilitates the discriminative map construction so that high-quality correspondences can be provided for generating the pseudo target point cloud. Based on the observation that the outlier has the significant structure-wise difference between its source neighborhood and corresponding pseudo target neighborhood while this difference for inlier is small, the inlier evaluation module exploits this difference to score the inlier confidence for each estimated correspondence. In particular, we construct an effective graph representation for capturing this geometric difference between the neighborhoods. Finally, with the learned correspondences and the corresponding inlier confidence, we use the weighted SVD algorithm for transformation estimation. Under the unsupervised setting, we exploit the Huber function based global alignment loss, the local neighborhood consensus loss, and spatial consistency loss for model optimization. The experimental results on extensive datasets demonstrate that our unsupervised point cloud registration method can yield comparable performance. Our code is available at https://github.com/supersyq/RIENet.

show abstract

“…Descriptors such as scale-invariant heat kernel signatures (SIHKS) [38], shape diameter function (SDF) [23], Gaussian curvature (GC) [7] and so on, are widely used for this task. In recent years, deep learning-based methods demonstrated great success in many fields of computer vision [14,3,32,41,13]. For 3D shape segmentation, PointNet [18] firstly proposed an efficient way to directly learn the features from unordered 3D point sets.…”

Section: Related Workmentioning

confidence: 99%

Meta-Learning 3D Shape Segmentation Functions

Hao,

Fang

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Learning robust 3D shape segmentation functions with deep neural networks has emerged as a powerful paradigm, offering promising performance in producing a consistent part segmentation of each 3D shape. Generalizing across 3D shape segmentation functions requires robust learning of priors over the respective function space and enables consistent part segmentation of shapes in presence of significant 3D structure variations. Existing generalization methods rely on extensive training of 3D shape segmentation functions on large-scale labeled datasets. In this paper, we proposed to formalize the learning of a 3D shape segmentation function space as a meta-learning problem, aiming to predict a 3D segmentation model that can be quickly adapted to new shapes with no or limited training data. More specifically, we define each task as unsupervised learning of shape-conditioned 3D segmentation function which takes as input points in 3D space and predicts the part-segment labels. The 3D segmentation function is trained by a self-supervised 3D shape reconstruction loss without the need for part labels. Also, we introduce an auxiliary deep neural network as a meta-learner which takes as input a 3D shape and predicts the prior over the respective 3D segmentation function space. We show in experiments that our meta-learning approach, denoted as Meta-3DSeg, leads to improvements on unsupervised 3D shape segmentation over the conventional designs of deep neural networks for 3D shape segmentation functions.

show abstract

PC-Net: Unsupervised Point Correspondence Learning with Neural Networks

Cited by 20 publications

References 23 publications

Unsupervised Learning of 3D Point Set Registration

Unsupervised Learning of 3D Point Set Registration

Reliable Inlier Evaluation for Unsupervised Point Cloud Registration

Meta-Learning 3D Shape Segmentation Functions

Contact Info

Product

Resources

About