From Points to Parts: 3D Object Detection From Point Cloud With Part-Aware and Part-Aggregation Network

@article{Shi2021FromPT,
  title={From Points to Parts: 3D Object Detection From Point Cloud With Part-Aware and Part-Aggregation Network},
  author={Shaoshuai Shi and Zhe Wang and Jianping Shi and Xiaogang Wang and Hongsheng Li},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2021},
  volume={43},
  pages={2647-2664}
}
3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications. In this paper, we extend our preliminary work PointRCNN to a novel and strong point-cloud-based 3D object detection framework, the part-aware and aggregation neural network (Part-<inline-formula><tex-math notation="LaTeX">$A^2$</tex-math><alternatives><mml:math><mml:msup><mml:mi>A</mml:mi><mml:mn>2</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="shi-ieq1… Expand
PSANet: Pyramid Splitting and Aggregation Network for 3D Object Detection in Point Cloud
TLDR
A new backbone network is proposed to complete the cross-layer fusion of multi-scale BEV feature maps, which makes full use of various information for detection and has better performance in both 3D and BEV object detection compared with some previous state-of-the-art methods. Expand
KDA3D: Key-Point Densification and Multi-Attention Guidance for 3D Object Detection
In this paper, we propose a novel 3D object detector KDA3D, which achieves high-precision and robust classification, segmentation, and localization with the help of key-point densification andExpand
Slice-Based Instance and Semantic Segmentation for Low-Channel Roadside LiDAR Data
More and more scholars are committed to light detection and ranging (LiDAR) as a roadside sensor to obtain traffic flow data. Filtering and clustering are common methods to extract pedestrians andExpand
SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds
TLDR
SVGA-Net is proposed, a novel end-to-end trainable network which mainly contains voxel-graph module and sparse- to-dense regression module to achieve comparable 3D detection tasks from raw LIDAR data. Expand
PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection
TLDR
A novel two-stage approach, namely PC-RGNN, dealing with LiDAR-based 3D object detection challenges by two specific solutions, introducing a point cloud completion module and a graph neural network module, which comprehensively captures relations among points through a local-global attention mechanism as well as multi-scale graph based context aggregation. Expand
End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
TLDR
A new framework based on differentiable Change of Representation (CoR) modules that allow the entire PL pipeline to be trained end-to-end and is compatible with most state-of-the-art networks for both tasks and in combination with PointRCNN improves over PL consistently across all benchmarks. Expand
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. Expand
Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather
TLDR
This work addresses the challenging task of LiDARbased 3D object detection in foggy weather by simulating physically accurate fog into clear-weather scenes, so that the abundant existing real datasets captured in clear weather can be repurposed for this task. Expand
RoIFusion: 3D Object Detection From LiDAR and Vision
TLDR
A deep neural network architecture is proposed to efficiently fuse the multi-modality features for 3D object detection by leveraging the advantages of LIDAR and camera sensors by aggregating a small set of 3D Region of Interests (RoIs) in the point clouds with the corresponding 2D RoIs in the images. Expand
Cascaded Cross-Modality Fusion Network for 3D Object Detection
TLDR
A cascaded cross-modality fusion network (CCFNet), which includes a cascaded multi-scale fusion module (CMF) and a novel center 3D IoU loss to resolve two issues of LIDAR-RGB fusion-based 3D object detection. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 63 REFERENCES
PIXOR: Real-time 3D Object Detection from Point Clouds
TLDR
PIXOR is proposed, a proposal-free, single-stage detector that outputs oriented 3D object estimates decoded from pixel-wise neural network predictions that surpasses other state-of-the-art methods notably in terms of Average Precision (AP), while still runs at 10 FPS. Expand
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. Expand
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
  • Yin Zhou, Oncel Tuzel
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
TLDR
VoxelNet is proposed, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network and learns an effective discriminative representation of objects with various geometries, leading to encouraging results in3D detection of pedestrians and cyclists. Expand
Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
TLDR
This paper proposes to convert image-based depth maps to pseudo-LiDAR representations --- essentially mimicking the LiDAR signal, and achieves impressive improvements over the existing state-of-the-art in image- based performance. Expand
Complex-YOLO: An Euler-Region-Proposal for Real-Time 3D Object Detection on Point Clouds
TLDR
Complex-YOLO, a state of the art real-time 3D object detection network on point clouds only, is introduced and a specific Euler-Region-Proposal Network (E-RPN) is proposed to estimate the pose of the object by adding an imaginary and a real fraction to the regression network. Expand
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. Expand
PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
TLDR
This work evaluates PointFusion on two distinctive datasets: the KITTI dataset that features driving scenes captured with a lidar-camera setup, and the SUN-RGBD dataset that captures indoor environments with RGB-D cameras. Expand
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. Expand
GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
TLDR
This work leverages the off-the-shelf 2D object detector to efficiently obtain a coarse cuboid for each predicted 2D box and explores the 3D structure information of the object by employing the visual features of visible surfaces. Expand
Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction
TLDR
MonopolyPSR, a monocular 3D object detection method that leverages proposals and shape reconstruction, is presented and a novel projection alignment loss is devised to jointly optimize these tasks in the neural network to improve 3D localization accuracy. Expand
...
1
2
3
4
5
...