Fast Attention-Based Simplification of LiDAR Point Clouds for Object Detection and Classification

• URL: http://arxiv.org/abs/2603.07593v1
• Date: Sun, 08 Mar 2026 11:38:34 GMT
• Title: Fast Attention-Based Simplification of LiDAR Point Clouds for Object Detection and Classification
• Abstract summary: We propose an efficient learned point cloud simplification method for LiDAR data.<n>The method combines a feature embedding module with an attention-based sampling module to prioritize task-relevant regions.<n>We evaluate the method against farthest point sampling (FPS) and random sampling (RS) on 3D object detection on the KITTI dataset and on object classification across four datasets.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LiDAR point clouds are widely used in autonomous driving and consist of large numbers of 3D points captured at high frequency to represent surrounding objects such as vehicles, pedestrians, and traffic signs. While this dense data enables accurate perception, it also increases computational cost and power consumption, which can limit real-time deployment. Existing point cloud sampling methods typically face a trade-off: very fast approaches tend to reduce accuracy, while more accurate methods are computationally expensive. To address this limitation, we propose an efficient learned point cloud simplification method for LiDAR data. The method combines a feature embedding module with an attention-based sampling module to prioritize task-relevant regions and is trained end-to-end. We evaluate the method against farthest point sampling (FPS) and random sampling (RS) on 3D object detection on the KITTI dataset and on object classification across four datasets. The method was consistently faster than FPS and achieved similar, and in some settings better, accuracy, with the largest gains under aggressive downsampling. It was slower than RS, but it typically preserved accuracy more reliably at high sampling ratios.

Related papers

• UniFlow: Towards Zero-Shot LiDAR Scene Flow for Autonomous Vehicles via Cross-Domain Generalization [46.6187296172395]
  We learn general motion priors that transfer to diverse and unseen LiDAR sensors.<n>We propose UniFlow, a family of feedforward models that unifies and trains on multiple large-scale LiDAR scene flow datasets.<n>UniFlow achieves state-of-the-art accuracy on unseen datasets like TruckScenes, outperforming prior TruckScenes-specific models by 30.1%.
  arXiv  Detail & Related papers  (2025-11-23T02:51:42Z)
• PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection [66.94819989912823]
  We propose a point-trajectory transformer with long short-term memory for efficient temporal 3D object detection. We use point clouds of current-frame objects and their historical trajectories as input to minimize the memory bank storage requirement. We conduct extensive experiments on the large-scale dataset to demonstrate that our approach performs well against state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-13T18:59:13Z)
• PV-SSD: A Multi-Modal Point Cloud Feature Fusion Method for Projection Features and Variable Receptive Field Voxel Features [1.5338480419018068]
  Real-time inference from extremely sparse 3D data is a formidable challenge. To address this problem, a typical class of approaches transforms the point cloud cast into a regular data representation. This paper proposes a multi-modal point cloud feature fusion method for projection features and variable receptive field voxel features.
  arXiv  Detail & Related papers  (2023-08-13T15:30:02Z)
• Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions [77.32043242988738]
  We propose a new framework for accurate point cloud upsampling that supports arbitrary upsampling rates. Our method first interpolates the low-res point cloud according to a given upsampling rate.
  arXiv  Detail & Related papers  (2023-04-24T06:36:35Z)
• IC-FPS: Instance-Centroid Faster Point Sampling Module for 3D Point-base Object Detection [0.5249805590164902]
  Our research focuses on tackling low efficiency issue of point-based methods on large-scale point clouds. Existing point-based methods adopt farthest point sampling (FPS) strategy for downsampling, which is computationally expensive in terms of inference time and memory consumption when the number of point cloud increases. We propose a novel Instance-Centroid Faster Point Sampling Module (IC-FPS) which effectively replaces the first Set Abstraction (SA) layer that is extremely tedious.
  arXiv  Detail & Related papers  (2023-03-31T09:31:29Z)
• Roadside Lidar Vehicle Detection and Tracking Using Range And Intensity Background Subtraction [0.0]
  We present the solution of roadside LiDAR object detection using a combination of two unsupervised learning algorithms. The method was validated against a commercial traffic data collection platform.
  arXiv  Detail & Related papers  (2022-01-13T00:54:43Z)
• Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approach [57.67932970472768]
  Mesh and Point Cloud simplification methods aim to reduce the complexity of 3D models while retaining visual quality and relevant salient features. We propose a fast point cloud simplification method by learning to sample salient points. The proposed method relies on a graph neural network architecture trained to select an arbitrary, user-defined, number of points from the input space and to re-arrange their positions so as to minimize the visual perception error.
  arXiv  Detail & Related papers  (2021-09-30T10:23:55Z)
• Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling [52.464516118826765]
  We introduce RandLA-Net, an efficient and lightweight neural architecture to infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Our RandLA-Net can process 1 million points in a single pass up to 200x faster than existing approaches.
  arXiv  Detail & Related papers  (2021-07-06T05:08:34Z)
• Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detection [59.765645791588454]
  Recently introduced RTS3D builds an efficient 4D Feature-Consistency Embedding space for the intermediate representation of object without depth supervision. We propose a shape prior non-uniform sampling strategy that performs dense sampling in outer region and sparse sampling in inner region. Our proposed method has 2.57% improvement on AP3d almost without extra network parameters.
  arXiv  Detail & Related papers  (2021-06-18T09:14:55Z)
• Lite-FPN for Keypoint-based Monocular 3D Object Detection [18.03406686769539]
  Keypoint-based monocular 3D object detection has made tremendous progress and achieved great speed-accuracy trade-off. We propose a sort of lightweight feature pyramid network called Lite-FPN to achieve multi-scale feature fusion. Our proposed method achieves significantly higher accuracy and frame rate at the same time.
  arXiv  Detail & Related papers  (2021-05-01T14:44:31Z)
• 3DSSD: Point-based 3D Single Stage Object Detector [61.67928229961813]
  We present a point-based 3D single stage object detector, named 3DSSD, achieving a good balance between accuracy and efficiency. Our method outperforms all state-of-the-art voxel-based single stage methods by a large margin, and has comparable performance to two stage point-based methods as well.
  arXiv  Detail & Related papers  (2020-02-24T12:01:58Z)

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.