paper-with-me

홈 › Papers

Transformers for Object Detection in Large Point Clouds

2022-09-30 · Felicia Ruppel, Florian Faion, Claudius Gläser, Klaus Dietmayer

We present TransLPC, a novel detection model for large point clouds that is based on a transformer architecture. While object detection with transformers has been an active field of research, it has proved difficult to apply such models to point clouds that span a large area, e.g. those that are common in autonomous driving, with lidar or radar data. TransLPC is able to remedy these issues: The structure of the transformer model is modified to allow for larger input sequence lengths, which are sufficient for large point clouds. Besides this, we propose a novel query refinement technique to improve detection accuracy, while retaining a memory-friendly number of transformer decoder queries. The queries are repositioned between layers, moving them closer to the bounding box they are estimating, in an efficient manner. This simple technique has a significant effect on detection accuracy, which is evaluated on the challenging nuScenes dataset on real-world lidar data. Besides this, the proposed method is compatible with existing transformer-based solutions that require object detection, e.g. for joint multi-object tracking and detection, and enables them to be used in conjunction with large point clouds.

📄 PDF Abstract BibTeX arXiv:2209.15258

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingDecoderMulti-Object TrackingObjectobject-detectionObject DetectionObject Tracking

Similar Papers 제목 키워드 기반

OctFormer: Octree-based Transformers for 3D Point Clouds

2023-05-04 · Peng-Shuai Wang

We propose octree-based transformers, named OctFormer, for 3D point cloud learning. OctFormer can not only serve as a general and effective backbone for 3D point cloud segmentation and object detection but also have line…

3D Object Detection3D Semantic SegmentationGPUobject-detection+3

Applying Plain Transformers to Real-World Point Clouds

2023-02-28 · Lanxiao Li, Michael Heizmann

To apply transformer-based models to point cloud understanding, many previous works modify the architecture of transformers by using, e.g., local attention and down-sampling. Although they have achieved promising results…

Inductive Biasobject-detectionObject DetectionSemantic Segmentation

SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds

2022-10-13 · Pei Sun, Mingxing Tan, Weiyue Wang, Chenxi Liu 외

3D object detection in point clouds is a core component for modern robotics and autonomous driving systems. A key challenge in 3D object detection comes from the inherent sparse nature of point occupancy within the 3D sc…

3D Object DetectionAutonomous DrivingObjectobject-detection+1

SEED: A Simple and Effective 3D DETR in Point Clouds

2024-07-15 · Zhe Liu, Jinghua Hou, Xiaoqing Ye, Tong Wang 외

Recently, detection transformers (DETRs) have gradually taken a dominant position in 2D detection thanks to their elegant framework. However, DETR-based detectors for 3D point clouds are still difficult to achieve satisf…

Group-Free 3D Object Detection via Transformers

2021-04-01 · ICCV 2021 10 · Ze Liu, Zheng Zhang, Yue Cao, Han Hu 외

Recently, directly detecting 3D objects from 3D point clouds has received increasing attention. To extract object representation from an irregular point cloud, existing methods usually take a point grouping step to assig…

3D Object DetectionObjectobject-detectionObject Detection