Corpus ID: 236318153

Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds

  title={Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds},
  author={Jiacheng Wei and Guosheng Lin and Kim-Hui Yap and Fayao Liu and Tzu-Yi Hung},
  • Jiacheng Wei, Guosheng Lin, +2 authors Tzu-Yi Hung
  • Published 2021
  • Computer Science
  • ArXiv
Semantic segmentation on 3D point clouds is an important task for 3D scene understanding. While dense labeling on 3D data is expensive and time-consuming, only a few works address weakly supervised semantic point cloud segmentation methods to relieve the labeling cost by learning from simpler and cheaper labels. Meanwhile, there are still huge performance gaps between existing weakly supervised methods and state-of-the-art fully supervised methods. In this paper, we train a semantic point cloud… Expand

Figures and Tables from this paper


Towards Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes
It is argued that 2D supervision is capable of providing sufficient guidance information for training 3D semantic segmentation models of natural scene point clouds while not explicitly capturing their inherent structures, even with only single view per training sample. Expand
Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point Clouds
This paper introduces a multi-path region mining module to generate pseudo point-level labels from a classification network trained with weak labels, and uses the point- level pseudo label to train a point cloud segmentation network in a fully supervised manner. Expand
Weakly Supervised Semantic Point Cloud Segmentation: Towards 10× Fewer Labels
  • Xun Xu, Gim Hee Lee
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
This work proposes a weakly supervised point cloud segmentation approach which requires only a tiny fraction of points to be labelled in the training stage, made possible by learning gradient approximation and exploitation of additional spatial and color smoothness constraints. Expand
JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds
This paper tackles the 3D semantic edge detection task for the first time and presents a new two-stream fully-convolutional network that jointly performs the two tasks and proposes a novel loss function that encourages the network to produce semantic segmentation results with better boundaries. Expand
Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation
A novel fusion-aware 3D point convolution which operates directly on the geometric surface being reconstructed and exploits effectively the inter-frame correlation for high-quality 3D feature learning is proposed. Expand
Boundary Perception Guidance: A Scribble-Supervised Semantic Segmentation Approach
This work presents a novel Boundary Perception Guidance approach, which consists of two basic components, i.e. prediction refinement and boundary regression, and employs class-agnostic edge maps for supervision to effectively guide the segmentation network in localizing the boundaries between different semantic regions. Expand
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Expand
3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation
3DMV is presented, a novel method for 3D semantic scene segmentation of RGB-D scans in indoor environments using a joint 3D-multi-view prediction network that achieves significantly better results than existing baselines. Expand
Learning Pixel-Level Semantic Affinity with Image-Level Supervision for Weakly Supervised Semantic Segmentation
  • Jiwoon Ahn, Suha Kwak
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
On the PASCAL VOC 2012 dataset, a DNN learned with segmentation labels generated by the method outperforms previous models trained with the same level of supervision, and is even as competitive as those relying on stronger supervision. Expand
3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
This work introduces new sparse convolutional operations that are designed to process spatially-sparse data more efficiently, and uses them to develop Spatially-Sparse Convolutional networks, which outperform all prior state-of-the-art models on two tasks involving semantic segmentation of 3D point clouds. Expand