From One to the Power of Many: Augmentations for Invariance to Multi-LiDAR Perception from Single-Sensor Datasets

• URL: http://arxiv.org/abs/2409.18592v1
• Date: Fri, 27 Sep 2024 09:51:45 GMT
• Title: From One to the Power of Many: Augmentations for Invariance to Multi-LiDAR Perception from Single-Sensor Datasets
• Authors: Marc Uecker, J. Marius Zöllner,
• Abstract summary: LiDAR perception methods for autonomous vehicles, powered by deep neural networks, have experienced steep growth in performance on classic benchmarks. There are still large gaps in performance when deploying models trained on single-sensor setups to modern multi-sensor vehicles. We propose some initial solutions in the form of application-specific data augmentations, which can facilitate better transfer to multi-sensor LiDAR setups.
• Score: 12.712896458348515
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, LiDAR perception methods for autonomous vehicles, powered by deep neural networks have experienced steep growth in performance on classic benchmarks, such as nuScenes and SemanticKITTI. However, there are still large gaps in performance when deploying models trained on such single-sensor setups to modern multi-sensor vehicles. In this work, we investigate if a lack of invariance may be responsible for these performance gaps, and propose some initial solutions in the form of application-specific data augmentations, which can facilitate better transfer to multi-sensor LiDAR setups. We provide experimental evidence that our proposed augmentations improve generalization across LiDAR sensor setups, and investigate how these augmentations affect the models' invariance properties on simulations of different LiDAR sensor setups.

Related papers

• LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splatting [50.808933338389686]
  LiDAR simulation plays a crucial role in closed-loop simulation for autonomous driving. We present LiDAR-GS, the first LiDAR Gaussian Splatting method, for real-time high-fidelity re-simulation of LiDAR sensor scans in public urban road scenes. Our approach succeeds in simultaneously re-simulating depth, intensity, and ray-drop channels, achieving state-of-the-art results in both rendering frame rate and quality on publically available large scene datasets.
  arXiv  Detail & Related papers  (2024-10-07T15:07:56Z)
• Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving [58.16024314532443]
  We introduce LaserMix++, a framework that integrates laser beam manipulations from disparate LiDAR scans and incorporates LiDAR-camera correspondences to assist data-efficient learning. Results demonstrate that LaserMix++ outperforms fully supervised alternatives, achieving comparable accuracy with five times fewer annotations. This substantial advancement underscores the potential of semi-supervised approaches in reducing the reliance on extensive labeled data in LiDAR-based 3D scene understanding systems.
  arXiv  Detail & Related papers  (2024-05-08T17:59:53Z)
• Is Your LiDAR Placement Optimized for 3D Scene Understanding? [8.233185931617122]
  prevailing driving datasets predominantly utilize single-LiDAR systems and collect data devoid of adverse conditions. We propose Place3D, a full-cycle pipeline that encompasses LiDAR placement optimization, data generation, and downstream evaluations. We showcase exceptional results in both LiDAR semantic segmentation and 3D object detection tasks, under diverse weather and sensor failure conditions.
  arXiv  Detail & Related papers  (2024-03-25T17:59:58Z)
• Traj-LIO: A Resilient Multi-LiDAR Multi-IMU State Estimator Through Sparse Gaussian Process [20.452961476175812]
  We introduce a multi-LiDAR multi-IMU state estimator by taking advantage of Gaussian Process (GP) Our proposed approach is capable of handling different sensor configurations and resilient to sensor failures. To contribute to the community, we will make our source code publicly available.
  arXiv  Detail & Related papers  (2024-02-14T14:08:06Z)
• Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features [69.47588461101925]
  We propose a method to adapt 3D object detectors to new driving environments. Our approach enhances LiDAR-based detection models using spatial quantized historical features. Experiments on real-world datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2023-09-21T15:00:31Z)
• Analysis of LiDAR Configurations on Off-road Semantic Segmentation Performance [0.6882042556551609]
  This paper investigates the impact of LiDAR configuration shifts on the performance of 3D LiDAR point cloud semantic segmentation models. A Cylinder3D model is trained and tested on simulated 3D LiDAR point cloud datasets created using the Mississippi State University Autonomous Vehicle Simulator (MAVS) and 32, 64 channel 3D LiDAR point clouds of the RELLIS-3D dataset collected in a real-world off-road environment.
  arXiv  Detail & Related papers  (2023-06-28T20:41:45Z)
• Instant Domain Augmentation for LiDAR Semantic Segmentation [10.250046817380458]
  This paper presents a fast and flexible LiDAR augmentation method for the semantic segmentation task, called 'LiDomAug'. Our on-demand augmentation module runs at 330 FPS, so it can be seamlessly integrated into the data loader in the learning framework.
  arXiv  Detail & Related papers  (2023-03-25T06:59:12Z)
• Learning to Simulate Realistic LiDARs [66.7519667383175]
  We introduce a pipeline for data-driven simulation of a realistic LiDAR sensor. We show that our model can learn to encode realistic effects such as dropped points on transparent surfaces. We use our technique to learn models of two distinct LiDAR sensors and use them to improve simulated LiDAR data accordingly.
  arXiv  Detail & Related papers  (2022-09-22T13:12:54Z)
• LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection [96.63947479020631]
  In many real-world applications, the LiDAR points used by mass-produced robots and vehicles usually have fewer beams than that in large-scale public datasets. We propose the LiDAR Distillation to bridge the domain gap induced by different LiDAR beams for 3D object detection.
  arXiv  Detail & Related papers  (2022-03-28T17:59:02Z)
• Learning Moving-Object Tracking with FMCW LiDAR [53.05551269151209]
  We propose a learning-based moving-object tracking method utilizing our newly developed LiDAR sensor, Frequency Modulated Continuous Wave (FMCW) LiDAR. Given the labels, we propose a contrastive learning framework, which pulls together the features from the same instance in embedding space and pushes apart the features from different instances to improve the tracking quality.
  arXiv  Detail & Related papers  (2022-03-02T09:11:36Z)
• Improving Perception via Sensor Placement: Designing Multi-LiDAR Systems for Autonomous Vehicles [16.45799795374353]
  We propose an easy-to-compute information-theoretic surrogate cost metric based on Probabilistic Occupancy Grids (POG) to optimize LiDAR placement for maximal sensing. Our results confirm that sensor placement is an important factor in 3D point cloud-based object detection and could lead to a variation of performance by 10% 20% on the state-of-the-art perception algorithms.
  arXiv  Detail & Related papers  (2021-05-02T01:52:18Z)

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.