Aligning Bird-Eye View Representation of Point Cloud Sequences using Scene Flow

• URL: http://arxiv.org/abs/2305.02909v1
• Date: Thu, 4 May 2023 15:16:21 GMT
• Title: Aligning Bird-Eye View Representation of Point Cloud Sequences using Scene Flow
• Authors: Minh-Quan Dao, Vincent Fr\'emont, Elwan H\'ery
• Abstract summary: Low-resolution point clouds are challenging for object detection methods due to their sparsity. We develop a plug-in module that enables single-frame detectors to compute scene flow to rectify their Bird-Eye View representation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Low-resolution point clouds are challenging for object detection methods due to their sparsity. Densifying the present point cloud by concatenating it with its predecessors is a popular solution to this challenge. Such concatenation is possible thanks to the removal of ego vehicle motion using its odometry. This method is called Ego Motion Compensation (EMC). Thanks to the added points, EMC significantly improves the performance of single-frame detectors. However, it suffers from the shadow effect that manifests in dynamic objects' points scattering along their trajectories. This effect results in a misalignment between feature maps and objects' locations, thus limiting performance improvement to stationary and slow-moving objects only. Scene flow allows aligning point clouds in 3D space, thus naturally resolving the misalignment in feature spaces. By observing that scene flow computation shares several components with 3D object detection pipelines, we develop a plug-in module that enables single-frame detectors to compute scene flow to rectify their Bird-Eye View representation. Experiments on the NuScenes dataset show that our module leads to a significant increase (up to 16%) in the Average Precision of large vehicles, which interestingly demonstrates the most severe shadow effect. The code is published at https://github.com/quan-dao/pc-corrector.

Related papers

• Ego-Motion Estimation and Dynamic Motion Separation from 3D Point Clouds for Accumulating Data and Improving 3D Object Detection [0.1474723404975345]
  One of high-resolution radar sensors, compared to lidar sensors, is the sparsity of the generated point cloud. This contribution analyzes limitations of accumulating radar point clouds on the View-of-Delft dataset. Experiments document an improved object detection performance by applying an ego-motion estimation and dynamic motion correction approach.
  arXiv  Detail & Related papers  (2023-08-29T14:53:16Z)
• DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking [67.34803048690428]
  We propose to model Dynamic Objects in RecurrenT (DORT) to tackle this problem. DORT extracts object-wise local volumes for motion estimation that also alleviates the heavy computational burden. It is flexible and practical that can be plugged into most camera-based 3D object detectors.
  arXiv  Detail & Related papers  (2023-03-29T12:33:55Z)
• GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flow [3.2738068278607426]
  We propose a GMA3D module based on the transformer framework to infer the motion information of occluded points from the motion information of local and global non-occluded points respectively. Experiments show that our GMA3D can solve the occlusion problem in the scene flow, especially in the real scene.
  arXiv  Detail & Related papers  (2022-10-07T03:09:00Z)
• Exploiting More Information in Sparse Point Cloud for 3D Single Object Tracking [9.693724357115762]
  3D single object tracking is a key task in 3D computer vision. The sparsity of point clouds makes it difficult to compute the similarity and locate the object. We propose a sparse-to-dense and transformer-based framework for 3D single object tracking.
  arXiv  Detail & Related papers  (2022-10-02T13:38:30Z)
• AGO-Net: Association-Guided 3D Point Cloud Object Detection Network [86.10213302724085]
  We propose a novel 3D detection framework that associates intact features for objects via domain adaptation. We achieve new state-of-the-art performance on the KITTI 3D detection benchmark in both accuracy and speed.
  arXiv  Detail & Related papers  (2022-08-24T16:54:38Z)
• CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud Learning [81.85951026033787]
  We set transformers in this work and incorporate them into a hierarchical framework for shape classification and part and scene segmentation. We also compute efficient and dynamic global cross attentions by leveraging sampling and grouping at each iteration. The proposed hierarchical model achieves state-of-the-art shape classification in mean accuracy and yields results on par with the previous segmentation methods.
  arXiv  Detail & Related papers  (2022-07-31T21:39:15Z)
• IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment [58.8330387551499]
  We formulate the problem as estimation of point-wise trajectories (i.e., smooth curves) We propose IDEA-Net, an end-to-end deep learning framework, which disentangles the problem under the assistance of the explicitly learned temporal consistency. We demonstrate the effectiveness of our method on various point cloud sequences and observe large improvement over state-of-the-art methods both quantitatively and visually.
  arXiv  Detail & Related papers  (2022-03-22T10:14:08Z)
• 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)
• 3D Object Tracking with Transformer [6.848996369226086]
  Feature fusion could make similarity computing more efficient by including target object information. Most existing LiDAR-based approaches directly use the extracted point cloud feature to compute similarity. In this paper, we propose a feature fusion network based on transformer architecture.
  arXiv  Detail & Related papers  (2021-10-28T07:03:19Z)
• Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection [64.2159881697615]
  Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. We propose a domain adaptation like approach to enhance the robustness of the feature representation. Our simple yet effective approach fundamentally boosts the performance of 3D point cloud object detection and achieves the state-of-the-art results.
  arXiv  Detail & Related papers  (2020-06-08T05:15:06Z)
• Boundary-Aware Dense Feature Indicator for Single-Stage 3D Object Detection from Point Clouds [32.916690488130506]
  We propose a universal module that helps 3D detectors focus on the densest region of the point clouds in a boundary-aware manner. Experiments on KITTI dataset show that DENFI improves the performance of the baseline single-stage detector remarkably.
  arXiv  Detail & Related papers  (2020-04-01T01:21:23Z)

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.