SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition

  title={SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud based Place Recognition},
  author={Yan Xia and Yusheng Xu and Shuang Li and Rui Wang and Juan Du and Daniel Cremers and Uwe Stilla},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Yan Xia, Yusheng Xu, Uwe Stilla
  • Published 24 November 2020
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We tackle the problem of place recognition from point cloud data and introduce a self-attention and orientation encoding network (SOE-Net) that fully explores the relationship between points and incorporates long-range context into point-wise local descriptors. Local information of each point from eight orientations is captured in a PointOE module, whereas long-range feature dependencies among local descriptors are captured with a self-attention unit. Moreover, we propose a novel loss function… 
ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion
The Siamese auto-encoder neural network is adopted to map the partial and complete input point cloud into a shared latent space, which can capture detailed shape prior and an iterative refinement unit is designed to generate complete shapes with fine-grained details by integrating prior information.
RPR-Net: A Point Cloud-based Rotation-aware Large Scale Place Recognition Network
This paper proposes a novel Point Cloud-based Rotation-aware Large Scale Place Recognition Network (RPR-Net), which achieves comparable results to existing state-of-the-art place recognition models and significantly outperforms other rotation-invariant baseline models when solving rotation problems.
AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition
A novel 3D LiDAR-based deep learning network (named AttDLNet) that comprises an encoder network and exploits an attention mechanism to selectively focus on long-range context and interfeature relationships is proposed.
TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fields
A novel method named TransLoc3D is proposed, utilizing adaptive receptive fields with a point-wise reweighting scheme to handle objects of different sizes while suppressing noises, and an external transformer to capture long-range feature dependencies.
InCloud: Incremental Learning for Point Cloud Place Recognition
This work introduces InCloud, a structure-aware distillation-based approach which preserves the higher-order structure of the network’s embedding space and is the first to effectively apply incremental learning for point cloud place recognition.
Pyramid Point Cloud Transformer for Large-Scale Place Recognition
A pyramid point cloud transformer network (PPT-Net) to learn the discriminative global descriptors from point clouds for efficient retrieval and achieves the state-of-the-art on the point cloud based place recognition task.
SVT-Net: A Super Light-Weight Network for Large Scale Place Recognition using Sparse Voxel Transformers
This work proposes model SVTNet, a super light-weight network, for large scale place recognition that can achieve state-of-art performance in terms of both accuracy and speed with a super-light model size (0.9M).
SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition
A super light-weight network model termed SVT-Net, consisting of ASVT and CSVT, which can achieve state-of-the-art performance in terms of both recognition accuracy and running speed with a super-light model size (0.9M parameters).
HiTPR: Hierarchical Transformer for Place Recognition in Point Cloud
This paper investigates the exploitation of transformer-based network for feature extraction, and proposes a Hierarchical Transformer for Place Recognition (HiTPR), which demonstrates the superiority of the HiTPR in terms of average recall rate.
Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training
A simple and effective learning- based method for computing a discriminative 3D point cloud descriptor for place recognition purposes, based on a sparse voxelized representation, enhanced with channel attention blocks.


PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval
This paper proposes a Point Contextual Attention Network (PCAN), which can predict the significance of each local point feature based on point context, and makes it possible to pay more attention to the task-relevent features when aggregating local features.
LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis
  • Zhe Liu, Shunbo Zhou, Yunhui Liu
  • Computer Science, Environmental Science
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
A novel deep neural network, named LPD-Net (Large-scale Place Description Network), which can extract discriminative and generalizable global descriptors from the raw 3D point cloud and reaches the state-of-the-art.
PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition
This paper proposes a combination/modification of the existing PointNet and NetVLAD, which allows end-to-end training and inference to extract the global descriptor from a given 3D point cloud, and proposes the "lazy triplet and quadruplet" loss functions that can achieve more discriminative and generalizable global descriptors to tackle the retrieval task.
DAGC: Employing Dual Attention and Graph Convolution for Point Cloud based Place Recognition
This paper introduces a Dual Attention module to help distinguish task-relevant features and to utilize other points' different contributions to a point to generate representation and introduces a Residual Graph Convolution Network module to aggregate local features of each point's multi-level neighbor points to further improve the representation.
PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation
Inspired by the outstanding 2D shape descriptor SIFT, a module called PointSIFT is designed that encodes information of different orientations and is adaptive to scale of shape, which outperforms state-of-the-art method on standard benchmark datasets.
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
A hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set and proposes novel set learning layers to adaptively combine features from multiple scales to learn deep point set features efficiently and robustly.
NetVLAD: CNN Architecture for Weakly Supervised Place Recognition
A convolutional neural network architecture that is trainable in an end-to-end manner directly for the place recognition task and an efficient training procedure which can be applied on very large-scale weakly labelled tasks are developed.
DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization
A Siamese network that jointly learns 3D local feature detection and description directly from raw 3D points and integrates FlexConv and Squeeze-and-Excitation to assure that the learned local descriptor captures multi-level geometric information and channel-wise relations.
Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification
A quadruplet deep network using a margin-based online hard negative mining is proposed based on the quadruplet loss for the person ReID, which can lead to the model output with a larger inter- class variation and a smaller intra-class variation compared to the triplet loss.
PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
Qualitative and quantitative evaluations of the PPFNet network suggest increased recall, improved robustness and invariance as well as a vital step in the 3D descriptor extraction performance.