DeepPoint3D: Learning discriminative local descriptors using deep metric learning on 3D point clouds

Srivastava, Siddharth; Lall, Brejesh

doi:10.1016/j.patrec.2019.02.027

Cited by 23 publications

(9 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lin et al [50] suggest a binary variant of the SHOT descriptor by utilising a Gray‐code encrypting scheme, while [51] proposes a binary variant of the HoD descriptor. In [52], the authors propose a deep‐learning based solution that directly processes unstructured 3D point clouds and learns a permutation invariant representation of the 3D vertices, while in [53] the authors utilise a deep network to directly match 2D with 3D features. For a systematic review on current feature descriptors the reader is referred to [54].…”

Section: 2d/3d Keypoint Detection and Feature Description Methodsmentioning

confidence: 99%

Performance evaluation of single and cross‐dimensional feature detection and description

2020

View full text Add to dashboard Cite

Three-dimensional local feature detection and description techniques are widely used for object registration and recognition applications. Although several evaluations of 3D local feature detection and description methods have already been published, these are constrained in a single dimensional scheme, i.e. either 3D or 2D methods that are applied onto multiple projections of the 3D data. However, cross-dimensional (mixed 2D and 3D) feature detection and description has yet to be investigated. Here, we evaluated the performance of both single and cross-dimensional feature detection and description methods on several 3D datasets and demonstrated the superiority of cross-dimensional over single-dimensional schemes. 2D / 3D Keypoint Detection and Feature Description Methods Keypoint DetectorsKeypoint detectors analyse the structure around a vertex or a pixel depending on the data domain (3D or 2D,

show abstract

Section: 2d/3d Keypoint Detection and Feature Description Methodsmentioning

confidence: 99%

Performance evaluation of single and cross‐dimensional feature detection and description

2020

View full text Add to dashboard Cite

show abstract

“…Qiao et al [40] introduced using a triplet loss to train an inductive ZSL model. More recently, Do et al [13] proposed a tight upper bound of the triplet loss by linearizing it using class centroids, Zakharov et al [72] explored the triplet loss in manifold learning, Srivastava et al [54] investigated weighting hard negative samples more than easy negatives, and Zhaoqun et al [32] proposed the angular triplet-center loss, a variant that reduces the similarity distance between features. Triplet loss related methods typically work under inductive settings, where the ground-truth label of an anchor point remains available during training.…”

Section: Related Workmentioning

confidence: 99%

Zero-shot Learning of 3D Point Cloud Objects

Cheraghian

Rahman

2019

2019 16th International Conference on Machine Vision Applications (MVA)

View full text Add to dashboard Cite

Recent deep learning architectures can recognize instances of 3D point cloud objects of previously seen classes quite well. At the same time, current 3D depth camera technology allows generating/segmenting a large amount of 3D point cloud objects from an arbitrary scene, for which there is no previously seen training data. A challenge for a 3D point cloud recognition system is, then, to classify objects from new, unseen, classes. This issue can be resolved by adopting a zero-shot learning (ZSL) approach for 3D data, similar to the 2D image version of the same problem. ZSL attempts to classify unseen objects by comparing semantic information (attribute/word vector) of seen and unseen classes. Here, we adapt several recent 3D point cloud recognition systems to the ZSL setting with some changes to their architectures. To the best of our knowledge, this is the first attempt to classify unseen 3D point cloud objects in the ZSL setting. A standard protocol (which includes the choice of datasets and the seen/unseen split) to evaluate such systems is also proposed. Baseline performances are reported using the new protocol on the investigated models. This investigation throws a new challenge to the 3D point cloud recognition community that may instigate numerous future works.

show abstract

“…Thus, it saves time and memory that is wasted on structure mapping of point clouds. DeepPoint3D [29] uses multi-margin contrastive loss for discriminative learning so that directly usable permutation invariant local descriptors can be learnt. Most of the approaches uses convolutional neural network but graph neural network (GCN) can also be used for semantic segmentation of 3D point cloud [17].…”

Section: Previous Workmentioning

confidence: 99%

Semantic Segmentation of Surface from Lidar Point Cloud

Mukherjee¹,

Das²,

Ghosh³

et al. 2020

Preprint

View full text Add to dashboard Cite

In the field of SLAM (Simultaneous Localization And Mapping) for robot navigation, mapping the environment is an important task. In this regard the Lidar sensor can produce near accurate 3D map of the environment in the format of point cloud, in real time. Though the data is adequate for extracting information related to SLAM, processing millions of points in the point cloud is computationally quite expensive. The methodology presented proposes a fast algorithm that can be used to extract semantically labelled surface segments from the cloud, in real time, for direct navigational use or higher level contextual scene reconstruction. First, a single scan from a spinning Lidar is used to generate a mesh of subsampled cloud points online. The generated mesh is further used for surface normal computation of those points on the basis of which surface segments are estimated. A novel descriptor to represent the surface segments is proposed and utilized to determine the surface class of the segments (semantic label) with the help of classifier. These semantic surface segments can be further utilized for geometric reconstruction of objects in the scene, or can be used for optimized trajectory planning by a robot. The proposed methodology is compared with number of point cloud segmentation methods and state of the art semantic segmentation methods to emphasize its efficacy in terms of speed and accuracy.

show abstract

DeepPoint3D: Learning discriminative local descriptors using deep metric learning on 3D point clouds

Cited by 23 publications

References 42 publications

Performance evaluation of single and cross‐dimensional feature detection and description

Performance evaluation of single and cross‐dimensional feature detection and description

Zero-shot Learning of 3D Point Cloud Objects

Semantic Segmentation of Surface from Lidar Point Cloud

Contact Info

Product

Resources

About