SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds

@article{Zhu2020SSNSS,
  title={SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds},
  author={Xinge Zhu and Yuexin Ma and Tai Wang and Yan Xu and Jianping Shi and Dahua Lin},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.02774}
}
Multi-class 3D object detection aims to localize and classify objects of multiple categories from point clouds. Due to the nature of point clouds, i.e. unstructured, sparse and noisy, some features benefit-ting multi-class discrimination are underexploited, such as shape information. In this paper, we propose a novel 3D shape signature to explore the shape information from point clouds. By incorporating operations of symmetry, convex hull and chebyshev fitting, the proposed shape sig-nature is… 
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
  • Xinge Zhu, Hui Zhou, Dahua Lin
  • Computer Science
    2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2021
TLDR
A new framework for the outdoor LiDAR segmentation is proposed, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern while maintaining these inherent properties.
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception
  • Xinge Zhu, Hui Zhou, Da Lin
  • Computer Science
    IEEE transactions on pattern analysis and machine intelligence
  • 2021
TLDR
A new framework for the outdoor LiDAR segmentation is proposed, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern while maintaining these inherent properties.
A Versatile Multi-View Framework for LiDAR-based 3D Object Detection with Guidance from Panoptic Segmentation
TLDR
This paper proposes a novel multi-task framework that jointly performs 3D object detection and panoptic segmentation and achieves state-of-the-art performance on nuScenes 3D Detection Benchmark with 67.3 NDS.
Object DGCNN: 3D Object Detection using Dynamic Graphs
TLDR
Object DGCNN is introduced, a streamlined architecture for 3D object detection from point clouds that removes the necessity of post-processing via object confidence aggregation or non-maximum suppression and provides a set-to-set distillation approach customized to 3D detection.
3D Object Detection with a Self-supervised Lidar Scene Flow Backbone
TLDR
The main contribution leverages learned and motion representations and combines a self-supervised backbone with a 3D detection head focusing mainly on the relation between the scene and detection tasks, which increases3D detection performance significantly.
Boosting 3D Object Detection by Simulating Multimodality on Point Clouds
This paper presents a new approach to boost a single-modality (LiDAR) 3D object detector by teaching it to sim-ulate features and responses that follow a multi-modality (LiDAR-image) detector. The
RAANet: Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Density Level Estimation
TLDR
Range-Aware Attention Network (RAANet), which extracts more powerful BEV features and generates superior 3D object detections, and proposes a novel auxiliary loss for density estimation to further enhance the detection accuracy of RAANet for occluded objects.
LiDAR R-CNN: An Efficient and Universal 3D Object Detector
TLDR
Comprehensive experimental results on real-world datasets like Waymo Open Dataset (WOD) and KITTI dataset with various popular detectors demonstrate the universality and superiority of the LiDAR R-CNN.
Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds.
TLDR
This paper proposes an Attentive Spatiotemporal Transformer GRU (AST-GRU), which contains a Spatial Transformer Attention (STA) module and a Temporal Trans transformer Attention (TTA) module that enhances the vanilla GRU to focus on small objects and better align the moving objects.
TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers
TLDR
The proposed TransFusion, a robust solution to LiDARcamera fusion with a soft-association mechanism to handle inferior image conditions, achieves state-of-the-art performance on large-scale datasets and is extended to the 3D tracking task.
...
...

References

SHOWING 1-10 OF 39 REFERENCES
Deep Hough Voting for 3D Object Detection in Point Clouds
TLDR
This work proposes VoteNet, an end-to-end 3D object detection network based on a synergy of deep point set networks and Hough voting that achieves state-of-the-art 3D detection on two large datasets of real 3D scans, ScanNet and SUN RGB-D with a simple design, compact model size and high efficiency.
STD: Sparse-to-Dense 3D Object Detector for Point Cloud
TLDR
This work proposes a two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD), and implements a parallel intersection-over-union (IoU) branch to increase awareness of localization accuracy, resulting in further improved performance.
Shape-based recognition of 3D point clouds in urban environments
TLDR
This paper quantitatively evaluate the design of a system for recognizing objects in 3D point clouds of urban environments and tradeoffs of different alternatives in a truthed part of a scan of Ottawa that contains approximately 100 million points and 1000 objects of interest.
Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
TLDR
This report presents the method which wins the nuScenes3D Detection Challenge, and proposes a balanced group-ing head to boost the performance for the categories withsimilar shapes, achieving state-of-the-art detection performance on thenuScenes dataset.
Multi-view 3D Object Detection Network for Autonomous Driving
TLDR
This paper proposes Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D bounding boxes and designs a deep fusion scheme to combine region-wise features from multiple views and enable interactions between intermediate layers of different paths.
Joint 3D Proposal Generation and Object Detection from View Aggregation
TLDR
This work presents AVOD, an Aggregate View Object Detection network for autonomous driving scenarios that uses LIDAR point clouds and RGB images to generate features that are shared by two subnetworks: a region proposal network (RPN) and a second stage detector network.
Frustum PointNets for 3D Object Detection from RGB-D Data
TLDR
This work directly operates on raw point clouds by popping up RGBD scans and leverages both mature 2D object detectors and advanced 3D deep learning for object localization, achieving efficiency as well as high recall for even small objects.
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
TLDR
This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.
PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud
TLDR
Extensive experiments on the 3D detection benchmark of KITTI dataset show that the proposed architecture outperforms state-of-the-art methods with remarkable margins by using only point cloud as input.
Multi-level Fusion Based 3D Object Detection from Monocular Images
  • Bin Xu, Zhenzhong Chen
  • Computer Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
TLDR
This paper introduces an end-to-end multi-level fusion based framework for 3D object detection from a single monocular image and demonstrates that the proposed algorithm significantly outperforms monocular state-of-the-art methods.
...
...