Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point Clouds

@article{Wei2020MultiPathRM,
  title={Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point Clouds},
  author={Jiacheng Wei and Guosheng Lin and Kim-Hui Yap and Tzu-Yi Hung and Lihua Xie},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={4383-4392}
}
Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labeled data. Using advanced depth sensors, collection of large scale 3D dataset is no longer a cumbersome process. However, manually producing point-level label on the large scale dataset is time and labor-intensive. In this paper, we propose a weakly supervised approach to predict point-level results using weak labels… Expand
SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network
TLDR
A semi-supervised semantic point cloud segmentation network, named SSPC-Net, where the labels of unlabeled points are inferred from the few annotated 3D points and the pseudo labels of the unsupervised superpoints are generated. Expand
Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds
TLDR
This paper proposes a cross-sample feature reallocating module to transfer similar features and therefore re-route the gradients across two samples with common classes and an intra- sample feature redistribution module to propagate supervision signals on unlabeled points across and within point cloud samples. Expand
Weakly Supervised Pseudo-Label assisted Learning for ALS Point Cloud Semantic Segmentation
TLDR
This study proposes a pseudo-label-assisted point cloud segmentation method with very few sparsely sampled labels that are normally randomly selected for each class, and indicates that this method achieved an equally competitive result compared to that using a full supervision scheme. Expand
Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud
TLDR
This work constructs a pretext task with a self-supervised learning to transfer the learned prior knowledge from a large amount of unlabeled point cloud to a weakly supervised network, and proposes an effectiveWeakly supervised method containing two components to solve the above problem. Expand
ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation
TLDR
A Region-based and Diversity-aware Active Learning (ReDAL) is proposed, a general framework for many deep learning approaches, aiming to automatically select only informative and diverse sub-scene regions for label acquisition, which highly outperforms previous active learning strategies. Expand
Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision
  • 2021
Learning semantics from unstructured 3D point clouds with fewer 1 labels, although a realistic problem, has been under-explored. While existing 2 weakly supervised methods can effectively learnExpand
GA-NET: Global Attention Network for Point Cloud Semantic Segmentation
TLDR
A global attention network for point cloud semantic segmentation is proposed, named as GA-Net, consisting of a point-independent global attention module and a points-dependent global attention modules for obtaining contextual information of 3D point clouds in this paper. Expand
Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion
TLDR
A novel sparse LiDAR point cloud semantic segmentation framework assisted by learned contextual shape priors is proposed, which inherently improves SS optimization through fully end-to-end training. Expand
3D Spatial Recognition without Spatially Labeled 3D
TLDR
WyPR is introduced, a Weakly-supervised framework for Point cloud Recognition, requiring only scene-level class tags as supervision, and can detect and segment objects in point cloud data without access to any spatial labels at training time. Expand
Unsupervised Point Cloud Object Co-segmentation by Co-contrastive Learning and Mutual Attention Sampling
This paper presents a new task, point cloud object cosegmentation, aiming to segment the common 3D objects in a set of point clouds. We formulate this task as an object point sampling problem, andExpand
...
1
2
...

References

SHOWING 1-10 OF 45 REFERENCES
Towards Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes
TLDR
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
Semantic Labeling and Instance Segmentation of 3D Point Clouds Using Patch Context Analysis and Multiscale Processing
TLDR
A novel algorithm for semantic segmentation and labeling of 3D point clouds of indoor scenes, where objects in point clouds can have significant variations and complex configurations, which outperforms state-of-the-art methods on several representative point cloud datasets. Expand
Unstructured Point Cloud Semantic Labeling Using Deep Segmentation Networks
TLDR
A new, general, and efficient method for unstructured point cloud labeling which applies CNNs on multiple 2D image views (or snapshots) of the point cloud using fully convolutional networks is described. Expand
MortonNet: Self-Supervised Learning of Local Features in 3D Point Clouds
TLDR
A self-supervised task on point clouds, in order to learn meaningful point-wise features that encode local structure around each point, results in features that are useful for 3D segmentation tasks, and generalize well to other datasets. Expand
Self-Supervised Deep Learning on Point Clouds by Reconstructing Space
TLDR
This work proposes a self-supervised learning task for deep learning on raw point cloud data in which a neural network is trained to reconstruct point clouds whose parts have been randomly rearranged, and demonstrates that pre-training with this method before supervised training improves the performance of state-of-the-art models and significantly improves sample efficiency. Expand
Interpolated Convolutional Networks for 3D Point Cloud Understanding
TLDR
A novel Interpolated Convolution operation, InterpConv, is proposed to tackle the point cloud feature learning and understanding problem, to utilize a set of discrete kernel weights and interpolate point features to neighboring kernel-weight coordinates by an interpolation function for convolution. Expand
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
TLDR
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
Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network
TLDR
A novel deep learning model for 3D point clouds is proposed, named Point2Sequence, to learn 3D shape features by capturing fine-grained contextual information in a novel implicit way, and achieves state-of-the-art performance in shape classification and segmentation tasks. Expand
Deep point-based scene labeling with depth mapping and geometric patch feature encoding
TLDR
A novel framework where the convolution operator is defined on depth maps around sampled points, which captures characteristics of local surface regions, and augment each point with feature encoding of the local geometric patches resulted from multi-method through patch pooling network (PPN). Expand
3DmFV: Three-Dimensional Point Cloud Classification in Real-Time Using Convolutional Neural Networks
TLDR
A novel, intuitively interpretable, 3-D point cloud representation called3-D modified Fisher vectors is proposed, which combines a coarse discrete grid structure with continuous generalized Fisher vectors and enables the design of a new CNN architecture for real-time point cloud classification. Expand
...
1
2
3
4
5
...