Stress-Testing LiDAR Registration

• URL: http://arxiv.org/abs/2204.07719v1
• Date: Sat, 16 Apr 2022 05:10:55 GMT
• Title: Stress-Testing LiDAR Registration
• Authors: Amnon Drory, Shai Avidan and Raja Giryes
• Abstract summary: We propose a method for selecting balanced registration sets, which are challenging sets of frame-pairs from LiDAR datasets. Perhaps unexpectedly, we find that the fastest and simultaneously most accurate approach is a version of advanced RANSAC.
• Score: 52.24383388306149
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Point cloud registration (PCR) is an important task in many fields including autonomous driving with LiDAR sensors. PCR algorithms have improved significantly in recent years, by combining deep-learned features with robust estimation methods. These algorithms succeed in scenarios such as indoor scenes and object models registration. However, testing in the automotive LiDAR setting, which presents its own challenges, has been limited. The standard benchmark for this setting, KITTI-10m, has essentially been saturated by recent algorithms: many of them achieve near-perfect recall. In this work, we stress-test recent PCR techniques with LiDAR data. We propose a method for selecting balanced registration sets, which are challenging sets of frame-pairs from LiDAR datasets. They contain a balanced representation of the different relative motions that appear in a dataset, i.e. small and large rotations, small and large offsets in space and time, and various combinations of these. We perform a thorough comparison of accuracy and run-time on these benchmarks. Perhaps unexpectedly, we find that the fastest and simultaneously most accurate approach is a version of advanced RANSAC. We further improve results with a novel pre-filtering method.

Related papers

• Probably Approximately Precision and Recall Learning [62.912015491907994]
  Precision and Recall are foundational metrics in machine learning. One-sided feedback--where only positive examples are observed during training--is inherent in many practical problems. We introduce a PAC learning framework where each hypothesis is represented by a graph, with edges indicating positive interactions.
  arXiv  Detail & Related papers  (2024-11-20T04:21:07Z)
• Finetuning Pre-trained Model with Limited Data for LiDAR-based 3D Object Detection by Bridging Domain Gaps [8.897884780881535]
  LiDAR-based 3D object detectors often fail to adapt well to target domains with different sensor configurations. Recent studies suggest that pre-trained backbones can be learned in a self-supervised manner with large-scale unlabeled LiDAR frames. We propose a novel method, called Domain Adaptive Distill-Tuning (DADT), to adapt a pre-trained model with limited target data.
  arXiv  Detail & Related papers  (2024-10-02T08:22:42Z)
• SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection [53.19618419772467]
  Single-frame infrared small target (SIRST) detection aims to recognize small targets from clutter backgrounds. With the development of Transformer, the scale of SIRST models is constantly increasing. With a rich diversity of infrared small target data, our algorithm significantly improves the model performance and convergence speed.
  arXiv  Detail & Related papers  (2024-03-08T16:14:54Z)
• 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)
• Accurate Point Cloud Registration with Robust Optimal Transport [16.386335031156005]
  We show that recent OT solvers improve both optimization-based and deep learning methods for point cloud registration. Our work demonstrates that robust OT enables fast pre-alignment and fine-tuning for a wide range of registration models.
  arXiv  Detail & Related papers  (2021-11-01T01:34:46Z)
• Improving Calibration for Long-Tailed Recognition [68.32848696795519]
  We propose two methods to improve calibration and performance in such scenarios. For dataset bias due to different samplers, we propose shifted batch normalization. Our proposed methods set new records on multiple popular long-tailed recognition benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-01T13:55:21Z)
• Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences [17.351635242415703]
  We study a novel setting of this problem: model-free single object tracking (SOT) SOT takes the object state in the first frame as input, and jointly solves state estimation and tracking in subsequent frames. We then propose an optimization-based algorithm called SOTracker based on point cloud registration, vehicle shapes, and motion priors.
  arXiv  Detail & Related papers  (2021-03-10T13:01:26Z)
• Cirrus: A Long-range Bi-pattern LiDAR Dataset [35.87501129332217]
  We introduce Cirrus, a new long-range bi-pattern LiDAR public dataset for autonomous driving tasks. Our platform is equipped with a high-resolution video camera and a pair of LiDAR sensors with a 250-meter effective range. In Cirrus, eight categories of objects are exhaustively annotated in the LiDAR point clouds for the entire effective range.
  arXiv  Detail & Related papers  (2020-12-05T03:18:31Z)
• AutoSimulate: (Quickly) Learning Synthetic Data Generation [70.82315853981838]
  We propose an efficient alternative for optimal synthetic data generation based on a novel differentiable approximation of the objective. We demonstrate that the proposed method finds the optimal data distribution faster (up to $50times$), with significantly reduced training data generation (up to $30times$) and better accuracy ($+8.7%$) on real-world test datasets than previous methods.
  arXiv  Detail & Related papers  (2020-08-16T11:36:11Z)

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.