Shuai Ma
Shuai Ma has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
Daixin Chen
ChengDu Aircraft Industrial (Group) Co., Ltd., Qingyang, Chengdu, China
2 shared publicationsLi Zhou
ChengDu Aircraft Industrial (Group) Co., Ltd., Qingyang, Chengdu, China
2 shared publicationsXusheng Zhu
ChengDu Aircraft Industrial (Group) Co., Ltd., Qingyang, Chengdu, China
2 shared publicationsHaibo Tang
Chengdu Aircraft industrial (Group) Co., Ltd., Chengdu, China
1 shared publication- Junpeng Xue
Robotic Satellite Key Laboratory of Sichuan Province, Sichuan University, Chengdu, Sichuan, China
1 shared publication - Kangjian Yang
Key Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu 610209, China
1 shared publication
Latest Publications
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (7) , 9901-9915
BD-TNet: Balanced Density-Aware Point Cloud Completion Method Assisted by Trie-Like Shape Prior Embedding Dictionary
Point cloud completion is a fundamental yet challenging task in 3D computer vision. While existing two-stage methods have made significant progress in shape completion, they often overlook the critical issue of point density imbalance, leading to geometrically unsound results with illusory completeness. In this paper, we propose BD-TNet, a novel balanced density-aware point cloud completion method that systematically addresses this overlooked problem. Specifically, we design a Partial-Connected U-Net structure that strategically reduces top-layer skip connections to rebalance the influence between explicit features of partial inputs and abstract features for predicting missing regions, thereby generating uniformly distributed seed points. Furthermore, we introduce EmbeddingTrie, a Trie-like hierarchical shape prior dictionary that enables adaptive multi-scale prior fusion through a divide-and-conquer strategy. To directly constrain local point density, we devise an Elastic Potential Energy Loss that models point clouds as spring systems, effectively guiding the optimization toward balanced distributions. We evaluate our method on PCN, ShapeNet-34/55, and KITTI datasets, and the results demonstrate that BD-TNet achieves state-of-the-art performance on Density-aware Chamfer Distance while producing visually superior, complete point clouds with balanced density distribution.
- 9 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (7) , 9901-9915
BD-TNet: Balanced Density-Aware Point Cloud Completion Method Assisted by Trie-Like Shape Prior Embedding Dictionary
Point cloud completion is a fundamental yet challenging task in 3D computer vision. While existing two-stage methods have made significant progress in shape completion, they often overlook the critical issue of point density imbalance, leading to geometrically unsound results with illusory completeness. In this paper, we propose BD-TNet, a novel balanced density-aware point cloud completion method that systematically addresses this overlooked problem. Specifically, we design a Partial-Connected U-Net structure that strategically reduces top-layer skip connections to rebalance the influence between explicit features of partial inputs and abstract features for predicting missing regions, thereby generating uniformly distributed seed points. Furthermore, we introduce EmbeddingTrie, a Trie-like hierarchical shape prior dictionary that enables adaptive multi-scale prior fusion through a divide-and-conquer strategy. To directly constrain local point density, we devise an Elastic Potential Energy Loss that models point clouds as spring systems, effectively guiding the optimization toward balanced distributions. We evaluate our method on PCN, ShapeNet-34/55, and KITTI datasets, and the results demonstrate that BD-TNet achieves state-of-the-art performance on Density-aware Chamfer Distance while producing visually superior, complete point clouds with balanced density distribution.
- Open Access
- 29 October 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-12
LRNet: lightweight attention-oriented residual fusion network for light field salient object detection
Light field imaging contains abundant scene structure information, which can improve the accuracy of salient object detection in challenging tasks and has received widespread attention. However, how to apply the abundant information of light field imaging to salient object detection still faces enormous challenges. In this paper, the lightweight attention and residual convLSTM network is proposed to address this issue, which is mainly composed of the lightweight attention-based feature enhancement module (LFM) and residual convLSTM-based feature integration module (RFM). The LFM can provide an attention map for each focal slice through the attention mechanism to focus on the features related to the object, thereby enhancing saliency features. The RFM leverages the residual mechanism and convLSTM to fully utilize the spatial structural information of focal slices, thereby achieving high-precision feature fusion. Experimental results on three publicly available light field datasets show that the proposed method surpasses the existing 17 state-of-the-art methods and achieves the highest score among five quantitative indicators.
- 29 October 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-12
Open AccessLRNet: lightweight attention-oriented residual fusion network for light field salient object detection
Light field imaging contains abundant scene structure information, which can improve the accuracy of salient object detection in challenging tasks and has received widespread attention. However, how to apply the abundant information of light field imaging to salient object detection still faces enormous challenges. In this paper, the lightweight attention and residual convLSTM network is proposed to address this issue, which is mainly composed of the lightweight attention-based feature enhancement module (LFM) and residual convLSTM-based feature integration module (RFM). The LFM can provide an attention map for each focal slice through the attention mechanism to focus on the features related to the object, thereby enhancing saliency features. The RFM leverages the residual mechanism and convLSTM to fully utilize the spatial structural information of focal slices, thereby achieving high-precision feature fusion. Experimental results on three publicly available light field datasets show that the proposed method surpasses the existing 17 state-of-the-art methods and achieves the highest score among five quantitative indicators.
- Open Access
- 2 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Journal
- Vol. 15 (3) , 1-7
MSaD-Net: A Mix Self-Attention Networks for 3D Point Cloud Denoising
In the process of acquiring 3D point cloud data, due to environmental interference or unstable scanning equipment, the acquired data often have noisy points. Recently, with the development of neural networks for point clouds, great progress has been made in deep learning-based point cloud denoising. However, most of the existing methods adopt a pointnet-like structure to predict point offsets. Simple pooling operation loses much important information, such as local neighborhood information, and global information. The loss of information makes the algorithm ineffective when dealing with some complex cases. In order to solve the above problems, we propose a self-attention-based point cloud denoising network architecture, through the Transformer structure, to establish long-range dependencies of the points. In addition, we propose a local information embedding module to fast select meaningful points and serve as the input of the Transformer. We also consider the correlation between channels of point cloud features and further introduce a channel attention module. Extensive experiments prove that our method outperforms existing methods, and maintains a high running speed.
- 2 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Journal
- Vol. 15 (3) , 1-7
Open AccessMSaD-Net: A Mix Self-Attention Networks for 3D Point Cloud Denoising
In the process of acquiring 3D point cloud data, due to environmental interference or unstable scanning equipment, the acquired data often have noisy points. Recently, with the development of neural networks for point clouds, great progress has been made in deep learning-based point cloud denoising. However, most of the existing methods adopt a pointnet-like structure to predict point offsets. Simple pooling operation loses much important information, such as local neighborhood information, and global information. The loss of information makes the algorithm ineffective when dealing with some complex cases. In order to solve the above problems, we propose a self-attention-based point cloud denoising network architecture, through the Transformer structure, to establish long-range dependencies of the points. In addition, we propose a local information embedding module to fast select meaningful points and serve as the input of the Transformer. We also consider the correlation between channels of point cloud features and further introduce a channel attention module. Extensive experiments prove that our method outperforms existing methods, and maintains a high running speed.
- Open Access
- 5 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Journal
- Vol. 14 (5) , 1-10
Deep Learning-Based Prediction Algorithm on Atmospheric Turbulence-Induced Wavefront for Adaptive Optics
Correction performance of an adaptive optics (AO) system is severely limited by its system latency under high temporal frequency distortions. Wavefront prediction methods has been proven to be an effective way to compensate system delay. A novel wavefront prediction method based on residual learning fusion network (RLFNet) is proposed in this paper. The network is able to eliminate redundant information between adjacent wavefront frames and fuse refined features, which provides a higher prediction accuracy under fewer priori wavefront input. The method is tested on a 1km laser atmospheric transmission experimental setup through high frequency atmospheric turbulence, where wavefront data is collected from a 1kHz Shack-Hartmann wavefront sensor (SHWS). We show that the proposed architecture is able to predict the second frame wavefront after the previous 6 frames with a root-mean-square (RMS) wavefront error reduction up to 53% compare to non-predictive method.
- 5 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Journal
- Vol. 14 (5) , 1-10
Open AccessDeep Learning-Based Prediction Algorithm on Atmospheric Turbulence-Induced Wavefront for Adaptive Optics
Correction performance of an adaptive optics (AO) system is severely limited by its system latency under high temporal frequency distortions. Wavefront prediction methods has been proven to be an effective way to compensate system delay. A novel wavefront prediction method based on residual learning fusion network (RLFNet) is proposed in this paper. The network is able to eliminate redundant information between adjacent wavefront frames and fuse refined features, which provides a higher prediction accuracy under fewer priori wavefront input. The method is tested on a 1km laser atmospheric transmission experimental setup through high frequency atmospheric turbulence, where wavefront data is collected from a 1kHz Shack-Hartmann wavefront sensor (SHWS). We show that the proposed architecture is able to predict the second frame wavefront after the previous 6 frames with a root-mean-square (RMS) wavefront error reduction up to 53% compare to non-predictive method.