3D Capsule Hand Pose Estimation Network Based on Structural Relationship Information

Wu, Yonghong; Ma, Shuangbao; Zhang, Dejun; Sun, Jun

doi:10.3390/sym12101636

Cited by 6 publications

(3 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, it is robust in the occlusion or undetected joints scenario and generalizes well for the in the wild scenario. In the future work, we will optimize our network [45,46] for better time performance and apply the idea of LCMDN into more extended fields, such as visual tracking [47], multi-view and multi-person pose estimation [46,48], or 3D human hand pose estimation [49].…”

Section: Discussionmentioning

confidence: 99%

An Improved Mixture Density Network for 3D Human Pose Estimation with Ordinal Ranking

Zhang

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Estimating accurate 3D human poses from 2D images remains a challenge due to the lack of explicit depth information in 2D data. This paper proposes an improved mixture density network for 3D human pose estimation called the Locally Connected Mixture Density Network (LCMDN). Instead of conducting direct coordinate regression or providing unimodal estimates per joint, our approach predicts multiple possible hypotheses by the Mixture Density Network (MDN). Our network can be divided into two steps: the 2D joint points are estimated from the input images first; then, the information of human joints correlation is extracted by a feature extractor. After the human pose feature is extracted, multiple pose hypotheses are generated via the hypotheses generator. In addition, to make better use of the relationship between human joints, we introduce the Locally Connected Network (LCN) as a generic formulation to replace the traditional Fully Connected Network (FCN), which is applied to a feature extraction module. Finally, to select the most appropriate 3D pose result, a 3D pose selector based on the ordinal ranking of joints is adopted to score the predicted pose. The LCMDN improves the representation capability and robustness of the original MDN method notably. Experiments are conducted on the Human3.6M and MPII dataset. The average Mean Per Joint Position Error (MPJPE) of our proposed LCMDN reaches 50 mm on the Human3.6M dataset, which is on par or better than the state-of-the-art works. The qualitative results on the MPII dataset show that our network has a strong generalization ability.

show abstract

Section: Discussionmentioning

confidence: 99%

An Improved Mixture Density Network for 3D Human Pose Estimation with Ordinal Ranking

Zhang

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The idea of structure and correlation learning can be adopted for related vision tasks other than 3D points processing. Hence, in the future, we plan to optimize our network and to apply the method to more vision scenarios [53][54][55].…”

Section: Discussionmentioning

confidence: 99%

PointSCNet: Point Cloud Structure and Correlation Learning Based on Space-Filling Curve-Guided Sampling

Chen

et al. 2021

Symmetry

Self Cite

View full text Add to dashboard Cite

Geometrical structures and the internal local region relationship, such as symmetry, regular array, junction, etc., are essential for understanding a 3D shape. This paper proposes a point cloud feature extraction network named PointSCNet, to capture the geometrical structure information and local region correlation information of a point cloud. The PointSCNet consists of three main modules: the space-filling curve-guided sampling module, the information fusion module, and the channel-spatial attention module. The space-filling curve-guided sampling module uses Z-order curve coding to sample points that contain geometrical correlation. The information fusion module uses a correlation tensor and a set of skip connections to fuse the structure and correlation information. The channel-spatial attention module enhances the representation of key points and crucial feature channels to refine the network. The proposed PointSCNet is evaluated on shape classification and part segmentation tasks. The experimental results demonstrate that the PointSCNet outperforms or is on par with state-of-the-art methods by learning the structure and correlation of point clouds effectively.

show abstract

“…With deep learning making great strides in the field of image processing [16][17][18][19][20], the convolutional neural network (CNN) also shows good application prospects in the field of single image dehazing. Many learning-based algorithms [21][22][23][24] have been proposed and achieved better performance over traditional algorithms.…”

Section: Introductionmentioning

confidence: 99%

Attention Optimized Deep Generative Adversarial Network for Removing Uneven Dense Haze

Zhao

Feng

et al. 2021

Symmetry

View full text Add to dashboard Cite

The existing dehazing algorithms are problematic because of dense haze being unevenly distributed on the images, and the deep convolutional dehazing network relying too greatly on large-scale datasets. To solve these problems, this paper proposes a generative adversarial network based on the deep symmetric Encoder-Decoder architecture for removing dense haze. To restore the clear image, a four-layer down-sampling encoder is constructed to extract the semantic information lost due to the dense haze. At the same time, in the symmetric decoder module, an attention mechanism is introduced to adaptively assign weights to different pixels and channels, so as to deal with the uneven distribution of haze. Finally, the framework of the generative adversarial network is generated so that the model achieves a better training effect on small-scale datasets. The experimental results showed that the proposed dehazing network can not only effectively remove the unevenly distributed dense haze in the real scene image, but also achieve great performance in real-scene datasets with less training samples, and the evaluation indexes are better than other widely used contrast algorithms.

show abstract

3D Capsule Hand Pose Estimation Network Based on Structural Relationship Information

Cited by 6 publications

References 51 publications

An Improved Mixture Density Network for 3D Human Pose Estimation with Ordinal Ranking

An Improved Mixture Density Network for 3D Human Pose Estimation with Ordinal Ranking

PointSCNet: Point Cloud Structure and Correlation Learning Based on Space-Filling Curve-Guided Sampling

Attention Optimized Deep Generative Adversarial Network for Removing Uneven Dense Haze

Contact Info

Product

Resources

About