Super Sparse 3D Object Detection

• URL: http://arxiv.org/abs/2301.02562v1
• Date: Thu, 5 Jan 2023 17:03:56 GMT
• Title: Super Sparse 3D Object Detection
• Authors: Lue Fan, Yuxue Yang, Feng Wang, Naiyan Wang, and Zhaoxiang Zhang
• Abstract summary: LiDAR-based 3D object detection contributes ever-increasingly to the long-range perception in autonomous driving. To enable efficient long-range detection, we first propose a fully sparse object detector termed FSD. FSD++ generates residual points, which indicate the point changes between consecutive frames.
• Score: 48.684300007948906
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As the perception range of LiDAR expands, LiDAR-based 3D object detection contributes ever-increasingly to the long-range perception in autonomous driving. Mainstream 3D object detectors often build dense feature maps, where the cost is quadratic to the perception range, making them hardly scale up to the long-range settings. To enable efficient long-range detection, we first propose a fully sparse object detector termed FSD. FSD is built upon the general sparse voxel encoder and a novel sparse instance recognition (SIR) module. SIR groups the points into instances and applies highly-efficient instance-wise feature extraction. The instance-wise grouping sidesteps the issue of the center feature missing, which hinders the design of the fully sparse architecture. To further enjoy the benefit of fully sparse characteristic, we leverage temporal information to remove data redundancy and propose a super sparse detector named FSD++. FSD++ first generates residual points, which indicate the point changes between consecutive frames. The residual points, along with a few previous foreground points, form the super sparse input data, greatly reducing data redundancy and computational overhead. We comprehensively analyze our method on the large-scale Waymo Open Dataset, and state-of-the-art performance is reported. To showcase the superiority of our method in long-range detection, we also conduct experiments on Argoverse 2 Dataset, where the perception range ($200m$) is much larger than Waymo Open Dataset ($75m$). Code is open-sourced at https://github.com/tusen-ai/SST.

Related papers

• SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection [22.120656021516695]
  SAFDNet is a straightforward yet highly effective architecture for fully sparse 3D object detection. We conducted extensive experiments on Open, nuScenes, and Argoverse2 datasets. SAFDNet surpassed the previous best hybrid detector HEDNet by 2.6% mAP while being 2.1x faster.
  arXiv  Detail & Related papers  (2024-03-09T06:48:19Z)
• HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds [19.1921315424192]
  3D object detection in point clouds is important for autonomous driving systems. A primary challenge in 3D object detection stems from the sparse distribution of points within the 3D scene. We propose HEDNet, a hierarchical encoder-decoder network for 3D object detection.
  arXiv  Detail & Related papers  (2023-10-31T07:32:08Z)
• Fully Sparse Fusion for 3D Object Detection [69.32694845027927]
  Currently prevalent multimodal 3D detection methods are built upon LiDAR-based detectors that usually use dense Bird's-Eye-View feature maps. Fully sparse architecture is gaining attention as they are highly efficient in long-range perception. In this paper, we study how to effectively leverage image modality in the emerging fully sparse architecture.
  arXiv  Detail & Related papers  (2023-04-24T17:57:43Z)
• VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking [78.25819070166351]
  We propose VoxelNext for fully sparse 3D object detection. Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies. Our strong sparse convolutional network VoxelNeXt detects and tracks 3D objects through voxel features entirely.
  arXiv  Detail & Related papers  (2023-03-20T17:40:44Z)
• 4D Unsupervised Object Discovery [53.561750858325915]
  We propose 4D unsupervised object discovery, jointly discovering objects from 4D data -- 3D point clouds and 2D RGB images with temporal information. We present the first practical approach for this task by proposing a ClusterNet on 3D point clouds, which is jointly optimized with a 2D localization network.
  arXiv  Detail & Related papers  (2022-10-10T16:05:53Z)
• Fully Sparse 3D Object Detection [57.05834683261658]
  We build a fully sparse 3D object detector (FSD) for long-range LiDAR-based object detection. FSD is built upon the general sparse voxel encoder and a novel sparse instance recognition (SIR) module. SIR avoids the time-consuming neighbor queries in previous point-based methods by grouping points into instances.
  arXiv  Detail & Related papers  (2022-07-20T17:01:33Z)
• 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)
• Embracing Single Stride 3D Object Detector with Sparse Transformer [63.179720817019096]
  In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Many 3D detectors directly follow the common practice of 2D detectors, which downsample the feature maps even after quantizing the point clouds. We propose Single-stride Sparse Transformer (SST) to maintain the original resolution from the beginning to the end of the network.
  arXiv  Detail & Related papers  (2021-12-13T02:12:02Z)

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.