DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection

• URL: http://arxiv.org/abs/2207.10909v2
• Date: Thu, 6 Apr 2023 13:19:37 GMT
• Title: DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection
• Authors: Jinrong Yang, Lin Song, Songtao Liu, Weixin Mao, Zeming Li, Xiaoping Li, Hongbin Sun, Jian Sun, Nanning Zheng
• Abstract summary: We propose a Dynamic Ball Query (DBQ) network to adaptively select a subset of input points according to the input features. It can be embedded into some state-of-the-art 3D detectors and trained in an end-to-end manner, which significantly reduces the computational cost.
• Score: 113.5418064456229
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many point-based 3D detectors adopt point-feature sampling strategies to drop some points for efficient inference. These strategies are typically based on fixed and handcrafted rules, making it difficult to handle complicated scenes. Different from them, we propose a Dynamic Ball Query (DBQ) network to adaptively select a subset of input points according to the input features, and assign the feature transform with a suitable receptive field for each selected point. It can be embedded into some state-of-the-art 3D detectors and trained in an end-to-end manner, which significantly reduces the computational cost. Extensive experiments demonstrate that our method can increase the inference speed by 30%-100% on KITTI, Waymo, and ONCE datasets. Specifically, the inference speed of our detector can reach 162 FPS on KITTI scene, and 30 FPS on Waymo and ONCE scenes without performance degradation. Due to skipping the redundant points, some evaluation metrics show significant improvements. Codes will be released at https://github.com/yancie-yjr/DBQ-SSD.

Related papers

• V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection [73.37781484123536]
  We introduce a highly performant 3D object detector for point clouds using the DETR framework. To address the limitation, we introduce a novel 3D Relative Position (3DV-RPE) method. We show exceptional results on the challenging ScanNetV2 benchmark.
  arXiv  Detail & Related papers  (2023-08-08T17:14:14Z)
• 3D Small Object Detection with Dynamic Spatial Pruning [62.72638845817799]
  We propose an efficient feature pruning strategy for 3D small object detection. We present a multi-level 3D detector named DSPDet3D which benefits from high spatial resolution. It takes less than 2s to directly process a whole building consisting of more than 4500k points while detecting out almost all objects.
  arXiv  Detail & Related papers  (2023-05-05T17:57:04Z)
• 3D Video Object Detection with Learnable Object-Centric Global Optimization [65.68977894460222]
  Correspondence-based optimization is the cornerstone for 3D scene reconstruction but is less studied in 3D video object detection. We propose BA-Det, an end-to-end optimizable object detector with object-centric temporal correspondence learning and featuremetric object bundle adjustment.
  arXiv  Detail & Related papers  (2023-03-27T17:39:39Z)
• Stratified Transformer for 3D Point Cloud Segmentation [89.9698499437732]
  Stratified Transformer is able to capture long-range contexts and demonstrates strong generalization ability and high performance. To combat the challenges posed by irregular point arrangements, we propose first-layer point embedding to aggregate local information. Experiments demonstrate the effectiveness and superiority of our method on S3DIS, ScanNetv2 and ShapeNetPart datasets.
  arXiv  Detail & Related papers  (2022-03-28T05:35:16Z)
• Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds [29.762645632148097]
  We propose a highly-efficient single-stage point-based 3D detector called IA-SSD. We exploit two learnable, task-oriented, instance-aware downsampling strategies to hierarchically select the foreground points. Experiments conducted on several large-scale detection benchmarks demonstrate the competitive performance of our IA-SSD.
  arXiv  Detail & Related papers  (2022-03-21T17:14:02Z)
• SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection [78.90102636266276]
  We propose a novel set abstraction method named Semantics-Augmented Set Abstraction (SASA) Based on the estimated point-wise foreground scores, we then propose a semantics-guided point sampling algorithm to help retain more important foreground points during down-sampling. In practice, SASA shows to be effective in identifying valuable points related to foreground objects and improving feature learning for point-based 3D detection.
  arXiv  Detail & Related papers  (2022-01-06T08:54:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.