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

doi:10.1109/cvpr42600.2020.00639

Cited by 344 publications

(343 citation statements)

References 26 publications

Supporting

Mentioning

342

Contrasting

Order By: Relevance

“…Without using correspondence labels, PPF-FoldNet uses an encoder–decoder network to reconstruct the local patch fed in [ 24 ]. D3Feat proposes a joint learning of keypoint detector and descriptor [ 25 ]. The D3Feat provides descriptors and keypoint scores globally for all points, which introduces extra cost during inference.…”

Section: Related Workmentioning

confidence: 99%

“…To find the correspondences, using distance among descriptors rather than Euclidean distance between points promises improvements in point cloud registration, especially when no good initial guess is available. Then, handcrafted descriptors [ 10 , 14 , 15 , 16 , 17 , 18 , 19 , 20 ] and learned descriptors [ 21 , 22 , 23 , 24 , 25 , 26 , 27 ] have been proposed during the last decades.…”

Section: Introductionmentioning

confidence: 99%

“…Although the learned point descriptors score better, their supervising usually requires extra labor to label the data. Those algorithms either get the correspondences from the matched point clouds [ 21 , 22 , 23 , 25 ], which is costly, or they are labeling the inter-point cloud relation [ 26 , 27 ], which is inefficient to train. Moreover, the existing models either train on patches, which is not globally learned for the scene [ 21 , 22 , 24 ], or learn the scene as the training loss works globally for the whole point cloud but comes with a triplet siamese loss that is not directly related to the true transformation [ 26 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Self-Supervised Point Set Local Descriptors for Point Cloud Registration

Yuan

Borrmann

Hou

et al. 2021

Sensors

View full text Add to dashboard Cite

Descriptors play an important role in point cloud registration. The current state-of-the-art resorts to the high regression capability of deep learning. However, recent deep learning-based descriptors require different levels of annotation and selection of patches, which make the model hard to migrate to new scenarios. In this work, we learn local registration descriptors for point clouds in a self-supervised manner. In each iteration of the training, the input of the network is merely one unlabeled point cloud. Thus, the whole training requires no manual annotation and manual selection of patches. In addition, we propose to involve keypoint sampling into the pipeline, which further improves the performance of our model. Our experiments demonstrate the capability of our self-supervised local descriptor to achieve even better performance than the supervised model, while being easier to train and requiring no data labeling.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-Supervised Point Set Local Descriptors for Point Cloud Registration

Yuan

Borrmann

Hou

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Besides, the perfect match [50] encodes the unstructured 3D point cloud into a smoothed density value (SDV) grid that is convenient for convolving and designing a Siamese CNN to learn the descriptors. The D3Feat [51] uses the kernel point convolution (KPConv) [52] to process irregular point clouds to learn the feature descriptors. There are less abundant studies on the learnable descriptors of fusion features.…”

Section: Learnable 3d Feature Descriptors Of Point Cloudsmentioning

confidence: 99%

GACM: A Graph Attention Capsule Model for the Registration of TLS Point Clouds in the Urban Scene

et al. 2021

View full text Add to dashboard Cite

Point cloud registration is the foundation and key step for many vital applications, such as digital city, autonomous driving, passive positioning, and navigation. The difference of spatial objects and the structure complexity of object surfaces are the main challenges for the registration problem. In this paper, we propose a graph attention capsule model (named as GACM) for the efficient registration of terrestrial laser scanning (TLS) point cloud in the urban scene, which fuses graph attention convolution and a three-dimensional (3D) capsule network to extract local point cloud features and obtain 3D feature descriptors. These descriptors can take into account the differences of spatial structure and point density in objects and make the spatial features of ground objects more prominent. During the training progress, we used both matched points and non-matched points to train the model. In the test process of the registration, the points in the neighborhood of each keypoint were sent to the trained network, in order to obtain feature descriptors and calculate the rotation and translation matrix after constructing a K-dimensional (KD) tree and random sample consensus (RANSAC) algorithm. Experiments show that the proposed method achieves more efficient registration results and higher robustness than other frontier registration methods in the pairwise registration of point clouds.

show abstract

“…Fortunately, deep learning based methods have powerful feature extraction capability relying on numerous data fittings. They have received high attention and have been widely utilized to extracting high-dimension features from order-less point clouds [29]- [38]. Generally speaking, there are three ways of feature extraction for point cloud.…”

Section: Introductionmentioning

confidence: 99%

WADE-Net: Weighted Aggregation with Density Estimation for Point Cloud Place Recognition

Liu¹,

Wang²,

Peng³

et al. 2021

APM

View full text Add to dashboard Cite

Point cloud based place recognition plays an important role in mobile robotics. In this paper, we propose a weighted aggregation method from structure information adaptively for point cloud place recognition. Firstly, to preserve the prior distributions and local geometric structures, we fuse learned hidden features with handcrafted features in the beginning. Secondly, we further extract and aggregate adaptively weighted features concerning density and relative spatial information from these fused features, named Weighted Aggregation with Density Estimation (WADE) module. Then, we conduct the WADE block iteratively to group the latent manifold structures. Finally, comparison results on two public datasets Oxford Robotcar and KITTI show that the proposed approach exceeds the comparison approaches on recall rate averagely 7% -8%.

show abstract

D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features

Cited by 344 publications

References 26 publications

Self-Supervised Point Set Local Descriptors for Point Cloud Registration

Self-Supervised Point Set Local Descriptors for Point Cloud Registration

GACM: A Graph Attention Capsule Model for the Registration of TLS Point Clouds in the Urban Scene

WADE-Net: Weighted Aggregation with Density Estimation for Point Cloud Place Recognition

Contact Info

Product

Resources

About