Self-Supervised Learning of Local Features in 3D Point Clouds

Thabet, Ali; Alwassel, Humam; Ghanem, Bernard

doi:10.1109/cvprw50498.2020.00477

Cited by 44 publications

(16 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the more popular Hilbert curve, also Z-order curves have been used in representation problems, though less frequently. For example, in [35] the Z-order curve is chosen because of its good balance between locality preservation and computational complexity to map the neighbourhood around a point in a 3D point cloud into a 1D sequence. These sequences are fed into a CNN to predict the displacement between the current and the next point.…”

Section: Related Workmentioning

confidence: 99%

The Effect of Space-filling Curves on the Efficiency of Hand Gesture Recognition Based on sEMG Signals

Tsinganos

Cornelis

et al. 2021

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Over the past few years, Deep learning (DL) has revolutionized the field of data analysis. Not only are the algorithmic paradigms changed, but also the performance in various classification and prediction tasks has been significantly improved with respect to the state-of-the-art, especially in the area of computer vision. The progress made in computer vision has produced a spillover in many other domains, such as biomedical engineering. Some recent works are directed towards surface electromyography (sEMG) based hand gesture recognition, often addressed as an image classification problem and solved using tools such as Convolutional Neural Networks (CNN). This paper extends our previous work on the application of the Hilbert space-filling curve for the generation of image representations from multi-electrode sEMG signals, by investigating how the Hilbert curve compares to the Peano- and Z-order space-filling curves. The proposed space-filling mapping methods are evaluated on a variety of network architectures and in some cases yield a classification improvement of at least 3%, when used to structure the inputs before feeding them into the original network architectures.

show abstract

Section: Related Workmentioning

confidence: 99%

The Effect of Space-filling Curves on the Efficiency of Hand Gesture Recognition Based on sEMG Signals

Tsinganos

Cornelis

et al. 2021

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

show abstract

“…Furthermore, SPLATNet [37] uses sparse bilateral convolutional layers to build the network, and SO-Net [18] proposes permutation invariant architectures for learning with unordered point clouds. SSNet [42] combines Morton-order curve and point-wise to conduct self-supervised learning. SPNet [21] uses a self-prediction for 3D instance and semantic segmentation of point clouds.…”

Section: Related Workmentioning

confidence: 99%

“…Apart from mIoU, mean accuracy (mAcc) is also used to evaluate the performance of our proposed model. In addition to comparing with the state-of-the-art pointbased [28,47,20,11,30,40,56,42,19,53,21,49] and voxel-based methods [6], we also compare with the newest point-voxel-based model [23]. Table 2 shows the results of all methods on S3DIS dataset, and Figure 4…”

Section: Part Segmentationmentioning

confidence: 99%

Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning

Zhou,

Cao,

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a new convolutional neural network, called Multi Voxel-Point Neurons Convolution (MVPConv), for fast and accurate 3D deep learning. The previous works adopt either individual point-based features or local-neighboring voxel-based features to process 3D model, which limits the performance of models due to the inefficient computation. Moreover, most of the existing 3D deep learning frameworks aim at solving one specific task, and only a few of them can handle a variety of tasks. Integrating both the advantages of the voxel and point-based methods, the proposed MVPConv can effectively increase the neighboring collection between point-based features and also promote the independence among voxel-based features. Simply replacing the corresponding convolution module with MVPConv, we show that MVPConv can fit in different backbones to solve a wide range of 3D tasks. Extensive experiments on benchmark datasets such as ShapeNet Part, S3DIS and KITTI for various tasks show that MVPConv improves the accuracy of the backbone (PointNet) by up to 36%, and achieves higher accuracy than the voxel-based model with up to 34× speedup. In addition, MVPConv also outperforms the state-of-the-art point-based models with up to 8× speedup. Notably, our MVPConv achieves better accuracy than the newest point-voxel-based model PVCNN (a model more efficient than PointNet) with lower latency.

show abstract

“…Point Cloud Recognition with Less Supervision: [30] proposes a self-supervised method to learn a point cloud representation by reassembling randomly split point clouds parts. MortonNet [36] uses Z-order to learn a feature with self-supervision. However, these two models cannot directly use the self-supervised learned feature for tasks like object classification, part segmentation, and semantic segmentation.…”

Section: Related Workmentioning

confidence: 99%

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

Wei

Lin

Yap

et al. 2020

Preprint

View full text Add to dashboard Cite

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 on 3D point clouds. We introduce our multi-path region mining module to generate pseudo point-level label from a classification network trained with weak labels. It mines the localization cues for each class from various aspects of the network feature using different attention modules. Then, we use the point-level pseudo labels to train a point cloud segmentation network in a fully supervised manner. To the best of our knowledge, this is the first method that uses cloud-level weak labels on raw 3D space to train a point cloud semantic segmentation network. In our setting, the 3D weak labels only indicate the classes that appeared in our input sample. We discuss both scene-and subcloud-level weakly labels on raw 3D point cloud data and perform in-depth experiments on them. On ScanNet[8] dataset, our result trained with subcloud-level labels is compatible with some fully supervised methods.

show abstract

Self-Supervised Learning of Local Features in 3D Point Clouds

Cited by 44 publications

References 13 publications

The Effect of Space-filling Curves on the Efficiency of Hand Gesture Recognition Based on sEMG Signals

The Effect of Space-filling Curves on the Efficiency of Hand Gesture Recognition Based on sEMG Signals

Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning

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

Contact Info

Product

Resources

About