RangeDet: In Defense of Range View for LiDAR-based 3D Object Detection

Fan, Lue; Xiong, Xuan; Wang, Feng; Wang, Naiyan; Zhang, Zhaoxiang

doi:10.1109/iccv48922.2021.00291

Cited by 171 publications

(61 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There exists some other works that exploit variability in depth along the vertical axis [2,3,5,6,11]. Though their work is conceptually similar to ours, they report improvements in contrast to this work.…”

Section: Related Worksupporting

confidence: 52%

Semi-Local Convolutions for LiDAR Scan Processing

Triess¹,

Polizzi²,

Zöllner³

2021

Preprint

View full text Add to dashboard Cite

A number of applications, such as mobile robots or automated vehicles, use LiDAR sensors to obtain detailed information about their three-dimensional surroundings. Many methods use image-like projections to efficiently process these LiDAR measurements and use deep convolutional neural networks to predict semantic classes for each point in the scan. The spatial stationary assumption enables the usage of convolutions. However, LiDAR scans exhibit large differences in appearance over the vertical axis. Therefore, we propose semi local convolution (SLC), a convolution layer with reduced amount of weight-sharing along the vertical dimension. We are first to investigate the usage of such a layer independent of any other model changes. Our experiments did not show any improvement over traditional convolution layers in terms of segmentation IoU or accuracy.

show abstract

Section: Related Worksupporting

confidence: 52%

Semi-Local Convolutions for LiDAR Scan Processing

Triess¹,

Polizzi²,

Zöllner³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…To address this issue, we take advantage of the Meta-Kernel block to extract the meta features by dynamically learning the weights from the relative Cartesian coordinates and range values. As in [16], the Meta-Kernel is designed to effectively locate objects in LiDAR scans by exploiting the geometric information from the Cartesian coordinates. In this paper, we employ it to capture the spatial and temporal information for semantic segmentation.…”

Section: Feature Extractionmentioning

confidence: 99%

“…In contrast to the direct fusion method, our proposed range residual image efficiently represents multi-frame point cloud information, which can improve the accuracy and the speed of training and testing under the limited computing resources. Since the range residual image obtained from spherical projection may not effectively capture the local geometric structures, we take advantage of the Meta-Kernel operator [16] to extract the meta features by dynamically learning the weights from the relative Cartesian coordinates and range values. Thus, it reduces the inconsistency between the 2D range image coordinates input and Cartesian coordinates output.…”

Section: Introductionmentioning

confidence: 99%

Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation

Wang¹,

Zhu²,

Zhang³

2022

Preprint

View full text Add to dashboard Cite

LiDAR sensor is essential to the perception system in autonomous vehicles and intelligent robots. To fulfill the realtime requirements in real-world applications, it is necessary to efficiently segment the LiDAR scans. Most of previous approaches directly project 3D point cloud onto the 2D spherical range image so that they can make use of the efficient 2D convolutional operations for image segmentation. Although having achieved the encouraging results, the neighborhood information is not wellpreserved in the spherical projection. Moreover, the temporal information is not taken into consideration in the single scan segmentation task. To tackle these problems, we propose a novel approach to semantic segmentation for LiDAR sequences named Meta-RangeSeg, where a novel range residual image representation is introduced to capture the spatial-temporal information. Specifically, Meta-Kernel is employed to extract the meta features, which reduces the inconsistency between the 2D range image coordinates input and Cartesian coordinates output. An efficient U-Net backbone is used to obtain the multi-scale features. Furthermore, Feature Aggregation Module (FAM) aggregates the meta features and multi-scale features, which tends to strengthen the role of range channel. We have conducted extensive experiments for performance evaluation on SemanticKITTI, which is the de-facto dataset for LiDAR semantic segmentation. The promising results show that our proposed Meta-RangeSeg method is more efficient and effective than the existing approaches. Our full implementation is publicly available at https://github.com/songw-zju/Meta-RangeSeg.

show abstract

“…Early approaches on 3D object detection from point cloud can be categorized into two classes. The first class of methods transform the point cloud into more compact representations, e.g., Birds-Eye-View (BEV) images [3,11,34], frontal-view range images [2,7,18], and volumetric features [14,43,51]. Yan et al [42] developed a sparse convolutional backbone to efficiently process the point clouds by encoding the point clouds into a 3D sparse tensor.…”

Section: Related Work 21 3d Object Detection From Point Cloudsmentioning

confidence: 99%

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds

He¹,

Li²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Transformer has demonstrated promising performance in many 2D vision tasks. However, it is cumbersome to compute the self-attention on large-scale point cloud data because point cloud is a long sequence and unevenly distributed in 3D space. To solve this issue, existing methods usually compute self-attention locally by grouping the points into clusters of the same size, or perform convolutional self-attention on a discretized representation. However, the former results in stochastic point dropout, while the latter typically has narrow attention fields. In this paper, we propose a novel voxel-based architecture, namely Voxel Set Transformer (VoxSeT), to detect 3D objects from point clouds by means of set-to-set translation. VoxSeT is built upon a voxel-based set attention (VSA) module, which reduces the self-attention in each voxel by two crossattentions and models features in a hidden space induced by a group of latent codes. With the VSA module, VoxSeT can manage voxelized point clusters with arbitrary size in a wide range, and process them in parallel with linear complexity. The proposed VoxSeT integrates the high performance of transformer with the efficiency of voxelbased model, which can be used as a good alternative to the convolutional and point-based backbones. VoxSeT reports competitive results on the KITTI and Waymo detection benchmarks. The source codes can be found at https://github.com/skyhehe123/VoxSeT.

show abstract

RangeDet: In Defense of Range View for LiDAR-based 3D Object Detection

Cited by 171 publications

References 34 publications

Semi-Local Convolutions for LiDAR Scan Processing

Semi-Local Convolutions for LiDAR Scan Processing

Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds

Contact Info

Product

Resources

About