Are We Hungry for 3D LiDAR Data for Semantic Segmentation? A Survey and Experimental Study

Gao, Biao; Pan, Yancheng; Li, Chengkun; Geng, Sibo; Zhao, Huijing

doi:10.48550/arxiv.2006.04307

Cited by 9 publications

(15 citation statements)

References 212 publications

(301 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each point in the scenes is annotated with one of the 13 semantic categories. S3DIS belongs to the category of static datasets [ 45 ], which are commonly used for point cloud classification tasks, but it is designed to be suitable even for Semantic Segmentation, Instance Segmentation, and Object Detection tasks. Its main application scenarios include robotics, augmented reality, and urban planning.…”

Section: Datasetsmentioning

confidence: 99%

Recent Advancements in Learning Algorithms for Point Clouds: An Updated Overview

Camuffo

Mari

Milani

2022

Sensors

View full text Add to dashboard Cite

Recent advancements in self-driving cars, robotics, and remote sensing have widened the range of applications for 3D Point Cloud (PC) data. This data format poses several new issues concerning noise levels, sparsity, and required storage space; as a result, many recent works address PC problems using Deep Learning (DL) solutions thanks to their capability to automatically extract features and achieve high performances. Such evolution has also changed the structure of processing chains and posed new problems to both academic and industrial researchers. The aim of this paper is to provide a comprehensive overview of the latest state-of-the-art DL approaches for the most crucial PC processing operations, i.e., semantic scene understanding, compression, and completion. With respect to the existing reviews, the work proposes a new taxonomical classification of the approaches, taking into account the characteristics of the acquisition set up, the peculiarities of the acquired PC data, the presence of side information (depending on the adopted dataset), the data formatting, and the characteristics of the DL architectures. This organization allows one to better comprehend some final performance comparisons on common test sets and cast a light on the future research trends.

show abstract

Section: Datasetsmentioning

confidence: 99%

Recent Advancements in Learning Algorithms for Point Clouds: An Updated Overview

Camuffo

Mari

Milani

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…There are some DL-based methods being proposed recently for the weakly supervised point cloud segmentation task [40,27,36,9,60,20,7,12,56,10,51,30]. For example, Wang et al [39] proposed to generate point cloud segmentation labels by back-projecting 2D image annotations to 3D spaces.…”

Section: Weakly Supervised Point Cloud Segmentationmentioning

confidence: 99%

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Wu¹,

Wu²,

Lin³

et al. 2022

Preprint

View full text Add to dashboard Cite

Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model training. However, existing methods remain challenging to accurately segment 3D point clouds since limited annotated data may lead to insufficient guidance for label propagation to unlabeled data. Considering the smoothness-based methods have achieved promising progress, in this paper, we advocate applying the consistency constraint under various perturbations to effectively regularize unlabeled 3D points. Specifically, we propose a novel DAT (Dual Adaptive Transformations) model for weakly supervised point cloud segmentation, where the dual adaptive transformations are performed via an adversarial strategy at both point-level and region-level, aiming at enforcing the local and structural smoothness constraints on 3D point clouds. We evaluate our proposed DAT model with two popular backbones on the large-scale S3DIS and ScanNet-V2 datasets. Extensive experiments demonstrate that our model can effectively leverage the unlabeled 3D points and achieve significant performance gains on both datasets, setting new state-of-the-art performance for weakly supervised point cloud segmentation.

show abstract

“…Data hunger problem [30] in existing public data-sets: the training data-sets used in recent researches are not suitable enough to train the networks for autonomous driving due to their subdivided classes and lack of training data for specific classes. The classes in training data-sets commonly used in existing research [29], [31]- [33] cover only indoor environments, not outdoor [33].…”

Section: Introductionmentioning

confidence: 99%

“…2, specific classes have a relatively small number of points than other classes. Addressing this data hunger problem [30] requires obtaining more labeled data of these specific classes with few points. However, the traditional method of generating real-world data for autonomous driving requires an enormous amount of time and cost for data collection and labeling.…”

Section: Introductionmentioning

confidence: 99%

Fast and Lite Point Cloud Semantic Segmentation for Autonomous Driving Utilizing LiDAR Synthetic Training Data

et al. 2022

View full text Add to dashboard Cite

In the autonomous car, perception with point cloud semantic segmentation helps obtain a wealth of information about the surrounding road environment. Despite the massive progress of recent researches, the existing machine learning networks are still insufficient for online applications of autonomous driving due to too subdivided classes, the lack of training data, and their heavy computing load. To solve these problems, we propose a fast and lite point cloud semantic segmentation network for autonomous driving, which utilizes LiDAR synthetic data to improve the performance by transfer learning. First, we modify the labeling classes and generate the LiDAR synthetic data-set for additional training to alleviate the lack of training data of the realistic data-set. Then, to lower the computing load, we adopt a projection-based method and apply a lightweight segmentation network to projected LiDAR images, which has drastically reduced computing. Finally, we verified and evaluated the proposed network in this paper through experiments. Experimental results show that the proposed network can perform the threedimensional point cloud semantic segmentation in an online way, in which the inference speed overwhelms the existing algorithms.

show abstract

Are We Hungry for 3D LiDAR Data for Semantic Segmentation? A Survey and Experimental Study

Cited by 9 publications

References 212 publications

Recent Advancements in Learning Algorithms for Point Clouds: An Updated Overview

Recent Advancements in Learning Algorithms for Point Clouds: An Updated Overview

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Fast and Lite Point Cloud Semantic Segmentation for Autonomous Driving Utilizing LiDAR Synthetic Training Data

Contact Info

Product

Resources

About