Self-Supervised Point Cloud Representation Learning via Separating Mixed Shapes

Sun, Chao; Zheng, Zhedong; Wang, Xiaohan; Xu, Mingliang; Yang, Yi

doi:10.1109/tmm.2022.3206664

Cited by 18 publications

(3 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second step is to complete reconstructing the occluded point cloud, and the final step is to use the encoder weights as the initialization for the downstream point cloud task. Sun et al [191] developed a novel self-supervised learning technique called Mixing and Disentangling (MD) for learning 3D point cloud representations in response to the enormous success of self-supervised learning. The authors combined two input shapes and demand that the model learn to distinguish the inputs from the mixed shape.…”

Section: Self-supervised Methodsmentioning

confidence: 99%

A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

Sarker,

Stone

et al. 2024

Machine Vision and Applications

View full text Add to dashboard Cite

Point cloud analysis has a wide range of applications in many areas such as computer vision, robotic manipulation, and autonomous driving. While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unordered, irregular and noisy 3D points. To stimulate future research, this paper analyzes recent progress in deep learning methods employed for point cloud processing and presents challenges and potential directions to advance this field. It serves as a comprehensive review on two major tasks in 3D point cloud processing-namely, 3D shape classification and semantic segmentation.

show abstract

Section: Self-supervised Methodsmentioning

confidence: 99%

A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

Sarker,

Stone

et al. 2024

Machine Vision and Applications

View full text Add to dashboard Cite

show abstract

“…Therefore, the model was utilized for diverse downstream tasks from classification to segmentation. Furthermore, Sun et.al [35] also focused on a pre-train model using mixing and disentangling for point clouds. Specifically, the work performed self-supervised learning and generated new point clouds by mixing multiple samples instead of training on large datasets.…”

Section: B Point-based Methodsmentioning

confidence: 99%

Local Graph Point Attention Network in Point Cloud Segmentation

Tran

Lee

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Exploiting global factors and embedding them directly into local graphs in point clouds are challenging due to dense points and irregular structure. To accomplish this goal, we propose a novel end-toend trainable graph attention network that extracts global features in terms of local graphs. Our network presents general local graph, which obtains the most fundamental features based on point order positions in different neighborhoods. Central point attention is introduced to share weights with neighboring points to reinforce central point impacts. As a result, one point in the specific local graph can obtain global features from corresponding ones in other neighborhoods but still focus on its area by encoded central point weight sharing. Experimental results on benchmark point cloud segmentation datasets demonstrate our proposed network's competitive performance. INDEX TERMS 3D point cloud, central point, local graph, point attention, segmentation.

show abstract

“…Differently, generative pre-training methods construct a pretext task by applying operations such as masking (Yu et al 2022;Wang et al 2021) and mixing (Sun et al 2022) to the original point cloud scene. Subsequently, the corresponding decoder and loss function are designed for a complete pre-training.…”

Section: Related Workmentioning

confidence: 99%

Less Is More: Label Recommendation for Weakly Supervised Point Cloud Semantic Segmentation

Pan,

Zhang,

Gao

et al. 2024

AAAI

View full text Add to dashboard Cite

Weak supervision has proven to be an effective strategy for reducing the burden of annotating semantic segmentation tasks in 3D space. However, unconstrained or heuristic weakly supervised annotation forms may lead to suboptimal label efficiency. To address this issue, we propose a novel label recommendation framework for weakly supervised point cloud semantic segmentation. Distinct from pre-training and active learning, the label recommendation framework consists of three stages: inductive bias learning, recommendations for points to be labeled, and point cloud semantic segmentation learning. In practice, we first introduce the point cloud upsampling task to induct inductive bias from structural information. During the recommendation stage, we present a cross-scene clustering strategy to generate centers of clustering as recommended points. Then we introduce a recommended point positions attention module LabelAttention to model the long-range dependency under sparse annotations. Additionally, we employ position encoding to enhance the spatial awareness of semantic features. Throughout the framework, the useful information obtained from inductive bias learning is propagated to subsequent semantic segmentation networks in the form of label positions. Experimental results demonstrate that our framework outperforms weakly supervised point cloud semantic segmentation methods and other methods for labeling efficiency on S3DIS and ScanNetV2, even at an extremely low label rate.

show abstract

Self-Supervised Point Cloud Representation Learning via Separating Mixed Shapes

Cited by 18 publications

References 58 publications

A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

Local Graph Point Attention Network in Point Cloud Segmentation

Less Is More: Label Recommendation for Weakly Supervised Point Cloud Semantic Segmentation

Contact Info

Product

Resources

About