Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Clouds

Deng, Shuang; Dong, Qiulei; Liu, Bo; Hu, Zhanyi

doi:10.48550/arxiv.2107.03601

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most works focus on developing SSL for object-centric point clouds [51,52] or indoor scenes [53,54,55], whose scale and diversity are much lower than the outdoor LiDAR point clouds [15,16]. Some other works [56,57,58] try to utilize SSL for 3D object detection on LiDAR data.…”

Section: Ssl In 3dmentioning

confidence: 99%

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

Kong¹,

Ren²,

Peng³

et al. 2022

Preprint

View full text Add to dashboard Cite

Densely annotating LiDAR point clouds is costly, which restrains the scalability of fully-supervised learning methods. In this work, we study the underexplored semi-supervised learning (SSL) in LiDAR segmentation. Our core idea is to leverage the strong spatial cues of LiDAR point clouds to better exploit unlabeled data. We propose LaserMix to mix laser beams from different LiDAR scans, and then encourage the model to make consistent and confident predictions before and after mixing. Our framework has three appealing properties: 1) Generic: LaserMix is agnostic to LiDAR representations (e.g., range view and voxel), and hence our SSL framework can be universally applied. 2) Statistically grounded: We provide a detailed analysis to theoretically explain the applicability of the proposed framework. 3) Effective: Comprehensive experimental analysis on popular LiDAR segmentation datasets (nuScenes, SemanticKITTI, and ScribbleKITTI) demonstrates our effectiveness and superiority. Notably, we achieve competitive results over fully-supervised counterparts with 2× to 5× fewer labels and improve the supervised-only baseline significantly by 10.8% on average. We hope this concise yet high-performing framework could facilitate future research in semi-supervised LiDAR segmentation. Code will be publicly available 2 . * Equal contribution. 2 https://github.com/ldkong1205/LaserMix.Preprint. Under review.

show abstract

Section: Ssl In 3dmentioning

confidence: 99%

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

Kong¹,

Ren²,

Peng³

et al. 2022

Preprint

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

“…There are some DL-based methods being proposed recently for the weakly supervised point cloud segmentation task [93][94][95][96][97][98][99][100][101][102][103][104]. For example, Wang et al [105] proposed to generate point cloud segmentation labels by back-projecting 2D image annotations to 3D spaces.…”

Section: Weakly Supervised Point Cloud Segmentationmentioning

confidence: 99%

2D and 3D visual understanding with limited supervision

Wu¹

View full text Add to dashboard Cite

under various perturbations to effectively regularize unlabeled 3D points. In particular, we propose a novel Dual Adaptive Transformations (DAT) 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. Secondly, in Chapter 6, we observe that the straightforward way of applying consistency constraints to weakly supervised point cloud segmentation has two major limitations: unsatisfied pseudo labels due to the conventional confidence-based selection and insufficient consistency constraints due to discarding unreliable pseudo labels. Therefore, we propose a novel Reliability-Adaptive Consistency Network (RAC-Net) to use both prediction confidence and model uncertainty to measure the reliability of pseudo labels and apply consistency training on all unlabeled points while with different consistency constraints for different points based on the reliability of corresponding pseudo labels.

show abstract

Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Clouds

Cited by 3 publications

References 0 publications

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

2D and 3D visual understanding with limited supervision

Contact Info

Product

Resources

About