3D Point Cloud Registration for Localization Using a Deep Neural Network Auto-Encoder

Elbaz, Gil; Avraham, Tamar; Fischer, Anath

doi:10.1109/cvpr.2017.265

Cited by 228 publications

(162 citation statements)

References 20 publications

Supporting

Mentioning

158

Contrasting

Unclassified

Order By: Relevance

“…Some recent works [39,9,5,1] propose to learn 3D descriptors leveraging the DNNs, and attempt to solve the 3D scene recognition and re-localization problem, in which obtaining accurate local matching results is not the goal. In order to achieve that, methods, as ICP, are still necessary for the registration refinement.…”

Section: Related Workmentioning

confidence: 99%

DeepVCP: An End-to-End Deep Neural Network for Point Cloud Registration

Wan

Zhou

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

298

168

View full text Add to dashboard Cite

We present DeepICP -a novel end-to-end learningbased 3D point cloud registration framework that achieves comparable registration accuracy to prior state-of-the-art geometric methods. Different from other keypoint based methods where a RANSAC procedure is usually needed, we implement the use of various deep neural network structures to establish an end-to-end trainable network. Our keypoint detector is trained through this end-to-end structure and enables the system to avoid the inference of dynamic objects, leverages the help of sufficiently salient features on stationary objects, and as a result, achieves high robustness. Rather than searching the corresponding points among existing points, the key contribution is that we innovatively generate them based on learned matching probabilities among a group of candidates, which can boost the registration accuracy. Our loss function incorporates both the local similarity and the global geometric constraints to ensure all above network designs can converge towards the right direction. We comprehensively validate the effectiveness of our approach using both the KITTI dataset and the Apollo-SouthBay dataset. Results demonstrate that our method achieves comparable or better performance than the state-of-the-art geometry-based methods. Detailed ablation and visualization analysis are included to further illustrate the behavior and insights of our network. The low registration error and high robustness of our method makes it attractive for substantial applications relying on the point cloud registration task.

show abstract

Section: Related Workmentioning

confidence: 99%

DeepVCP: An End-to-End Deep Neural Network for Point Cloud Registration

Wan

Zhou

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

298

168

View full text Add to dashboard Cite

show abstract

“…The approach was evaluated in realistic urban setting and in derelict buildings. Elbaz et al [19] used segments produced from a Random Sphere Cover Set -overlapping point cloud spheres where each point of the original point cloud could be part of more than one sphere. These spheres were then projected to 2D depth images and processed by a deep auto-encoder.…”

Section: Related Workmentioning

confidence: 99%

Learning to See the Wood for the Trees: Deep Laser Localization in Urban and Natural Environments on a CPU

Tinchev

Peñate-Sánchez

Fallon

2019

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Localization in challenging, natural environments such as forests or woodlands is an important capability for many applications from guiding a robot navigating along a forest trail to monitoring vegetation growth with handheld sensors. In this work we explore laser-based localization in both urban and natural environments, which is suitable for online applications. We propose a deep learning approach capable of learning meaningful descriptors directly from 3D point clouds by comparing triplets (anchor, positive and negative examples). The approach learns a feature space representation for a set of segmented point clouds that are matched between a current and previous observations. Our learning method is tailored towards loop closure detection resulting in a small model which can be deployed using only a CPU. The proposed learning method would allow the full pipeline to run on robots with limited computational payload such as drones, quadrupeds or UGVs.

show abstract

“…Elbaz et al . [EAF17] encode local 3D geometric structures using a deep neural network auto‐encoder for registration between a large‐scale point cloud and a close‐proximity scanned point cloud. However, these methods ignore the hierarchical representations in the process of features extracting and the size of the local neighbours would have influences to the final results.…”

Section: Related Workmentioning

confidence: 99%

“…3DFeat-Net [YL18] learns both 3D feature detector and descriptor for point cloud matching using weak supervision, which leverages on alignment and attention mechanisms to learn feature correspondences from GPS-/INS-tagged 3D point clouds. Elbaz et al [EAF17] encode local 3D geometric structures using a deep neural network auto-encoder for registration between a large-scale point cloud and a close-proximity scanned point cloud. However, these methods ignore the hierarchical representations in the process of features extracting and the size of the local neighbours would have influences to the final results.…”

Section: Learned Shape Descriptorsmentioning

confidence: 99%

SiamesePointNet: A Siamese Point Network Architecture for Learning 3D Shape Descriptor

Jian-hui

Wang

Mao

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

We present a novel deep learning approach to extract point‐wise descriptors directly on 3D shapes by introducing Siamese Point Networks, which contain a global shape constraint module and a feature transformation operator. Such geometric descriptor can be used in a variety of shape analysis problems such as 3D shape dense correspondence, key point matching and shape‐to‐scan matching. The descriptor is produced by a hierarchical encoder–decoder architecture that is trained to map geometrically and semantically similar points close to one another in descriptor space. Benefiting from the additional shape contrastive constraint and the hierarchical local operator, the learned descriptor is highly aware of both the global context and local context. In addition, a feature transformation operation is introduced in the end of our networks to transform the point features to a compact descriptor space. The feature transformation can make the descriptors extracted by our networks unaffected by geometric differences in shapes. Finally, an N‐tuple loss is used to train all the point descriptors on a complete 3D shape simultaneously to obtain point‐wise descriptors. The proposed Siamese Point Networks are robust to many types of perturbations such as the Gaussian noise and partial scan. In addition, we demonstrate that our approach improves state‐of‐the‐art results on the BHCP benchmark.

show abstract

3D Point Cloud Registration for Localization Using a Deep Neural Network Auto-Encoder

Cited by 228 publications

References 20 publications

DeepVCP: An End-to-End Deep Neural Network for Point Cloud Registration

DeepVCP: An End-to-End Deep Neural Network for Point Cloud Registration

Learning to See the Wood for the Trees: Deep Laser Localization in Urban and Natural Environments on a CPU

SiamesePointNet: A Siamese Point Network Architecture for Learning 3D Shape Descriptor

Contact Info

Product

Resources

About