IPOD: Intensive Point-based Object Detector for Point Cloud

By Zetong Yang, Yanan Sun, Shu Liu, Xiaoyong Shen, Jiaya Jia. 2018

178 citations recorded by the source corpus.

We present a novel 3D object detection framework, named IPOD, based on raw point cloud. It seeds object proposal for each point, which is the basic element. This paradigm provides us with high recall and high fidelity of information, leading to a suitable way to process point cloud data. We design an end-to-end trainable architecture, where features of all points within a proposal are extracted from the backbone network and achieve a proposal feature for final bounding inference. These features with both context information and precise point cloud coordinates yield improved performance. We conduct experiments on KITTI dataset, evaluating our performance in terms of 3D object detection, Bird's Eye View (BEV) detection and 2D object detection. Our method accomplishes new state-of-the-art , showing great advantage on the hard set.

Subfields: Computational Mechanics, Environmental Engineering, Geology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Jiaya Jia
2. Mingxing Tan
3. Wei Han
4. Fei Liu
5. Alan L. Yuille
6. Michael A. Chapman
7. Patrick Nguyen
8. Yuchao Dai

In Environmental Engineering

1. Jiaya Jia
2. Shu Liu
3. Xiaoyong Shen
4. Zhixin Wang
5. K. Jia
6. Oscar Beijbom
7. Sourabh Vora
8. Alex H. Lang

In Geology

1. Jiaya Jia
2. Shu Liu
3. Sourabh Vora
4. Bassam Helou
5. Oscar Beijbom
6. Alex H. Lang
7. Alan L. Yuille
8. Yuchao Dai

Citations in the corpus

• A Survey of Autonomous Driving: Common Practices and Emerging Technologies (2019, neutral): “ccuracy. These algorithms only use pointcloud data. Algorithm T [s] Easy Moderate Hard PointRCNN [179] 0.10 85.9 75.8 68.3 PointPillars [180] 0.02 79.1 75.0 68.3 SECOND [140] 0.04 83.1 73.7 66.2 IPOD [181] 0.20 82.1 72.6 66.3 F-PointNet [182] 0.17 81.2 70.4 62.2 VoxelNet (Lidar) [167] 0.23 77.5 65.1”
• Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review (2020, background): “To be more specific, PointPainting [66] follows the idea of projecting points to 2D semantic maps in [61].”
• Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal (2019, methodology): “For multi-stage methods [13], [22], [23], subsequent works of IPOD [22] and PointRCNN [23] explore different proposal methods.”
• IoU Loss for 2D/3D Object Detection (2019, background): “We have listed nearly all the top results with publications here including: multi-modalities fusionbased [24, 8, 25, 26, 27, 28], one-stage- [10, 9, 11] and twostage-based [12] approaches.”
• StarNet: Targeted Computation for Object Detection in Point Clouds (2019, methodology): “Other works propose bounding boxes through a computationally intensive, learned proposal system operating on paired camera images [48, 31], with the goal of improving predictive performance by leveraging a camera image to seed a proposal system to maximize recall.”
• Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review (2020, methodology): “In [119], the PointNet++ [12] is applied to generate perpoint feature within the whole input point clouds.”
• Fast Point R-CNN (2019, background): “PointRCNN [29] and IPOD [41], concurrent with our work, generate point-wise proposals on Point Clouds, which consumes much computation on point-wise calculation in the similar region or background region.”
• PointPainting: Sequential Fusion for 3D Object Detection (2019, methodology): “Frustrum Point-Net [17] and ConvNet [25] use the 2D detections to limit the search space inside the frustum while IPOD [30] uses semantic segmentation outputs to seed the 3D proposal.”
• DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection (2022, background): “Following them, [22, 24, 31, 42] also learn features with PointNet-like [25] layers.”