I-PAttnGAN: An Image-Assisted Point Cloud Generation Method Based on Attention Generative Adversarial Network
The key to building a 3D point cloud map is to ensure the consistency and accuracy of point cloud data. However, the hardware limitations of LiDAR lead to a sparse and uneven distribution of point cloud data in the edge region, which brings many challenges to 3D map construction, such as low registr...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/1/153 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548995624697856 |
|---|---|
| author | Wenwen Li Yaxing Chen Qianyue Fan Meng Yang Bin Guo Zhiwen Yu |
| author_facet | Wenwen Li Yaxing Chen Qianyue Fan Meng Yang Bin Guo Zhiwen Yu |
| author_sort | Wenwen Li |
| collection | DOAJ |
| description | The key to building a 3D point cloud map is to ensure the consistency and accuracy of point cloud data. However, the hardware limitations of LiDAR lead to a sparse and uneven distribution of point cloud data in the edge region, which brings many challenges to 3D map construction, such as low registration accuracy and high construction errors in the sparse regions. To solve these problems, this paper proposes the I-PAttnGAN network to generate point clouds with image-assisted approaches, which aims to improve the density and uniformity of sparse regions and enhance the representation ability of point cloud data in sparse edge regions for distant objects. I-PAttnGAN uses the normalized flow model to extract the point cloud attention weights dynamically and then integrates the point cloud weights into image features to learn the transformation relationship between the weighted image features and the point cloud distribution, so as to realize the adaptive generation of the point cloud density and resolution. Extensive experiments are conducted on ShapeNet and nuScenes datasets. The results show that I-PAttnGAN significantly improves the performance of generating high-quality, dense point clouds in low-density regions compared with existing methods: the Chamfer distance value is reduced by about 2 times, the Earth Mover’s distance value is increased by 1.3 times, and the F1 value is increased by about 1.5 times. In addition, the effectiveness of the newly added modules is verified by ablation experiments, and the experimental results show that these modules play a key role in the generation process. Overall, the proposed model shows significant advantages in terms of accuracy and efficiency, especially in generating complete spatial point clouds. |
| format | Article |
| id | doaj-art-6a30dd53645b4d438b9e6094628080c7 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-6a30dd53645b4d438b9e6094628080c72025-01-10T13:20:24ZengMDPI AGRemote Sensing2072-42922025-01-0117115310.3390/rs17010153I-PAttnGAN: An Image-Assisted Point Cloud Generation Method Based on Attention Generative Adversarial NetworkWenwen Li0Yaxing Chen1Qianyue Fan2Meng Yang3Bin Guo4Zhiwen Yu5Department of Computer Science, Northwestern Polytechnical University, No. 127 West Youyi Road, Xi’an 710072, ChinaDepartment of Computer Science, Northwestern Polytechnical University, No. 127 West Youyi Road, Xi’an 710072, ChinaDepartment of Computer Science, Northwestern Polytechnical University, No. 127 West Youyi Road, Xi’an 710072, ChinaDepartment of Artificial Intelligence, Xi’an Jiaotong University, No. 28 Xianning West Road, Xi’an 710049, ChinaDepartment of Computer Science, Northwestern Polytechnical University, No. 127 West Youyi Road, Xi’an 710072, ChinaDepartment of Computer Science, Northwestern Polytechnical University, No. 127 West Youyi Road, Xi’an 710072, ChinaThe key to building a 3D point cloud map is to ensure the consistency and accuracy of point cloud data. However, the hardware limitations of LiDAR lead to a sparse and uneven distribution of point cloud data in the edge region, which brings many challenges to 3D map construction, such as low registration accuracy and high construction errors in the sparse regions. To solve these problems, this paper proposes the I-PAttnGAN network to generate point clouds with image-assisted approaches, which aims to improve the density and uniformity of sparse regions and enhance the representation ability of point cloud data in sparse edge regions for distant objects. I-PAttnGAN uses the normalized flow model to extract the point cloud attention weights dynamically and then integrates the point cloud weights into image features to learn the transformation relationship between the weighted image features and the point cloud distribution, so as to realize the adaptive generation of the point cloud density and resolution. Extensive experiments are conducted on ShapeNet and nuScenes datasets. The results show that I-PAttnGAN significantly improves the performance of generating high-quality, dense point clouds in low-density regions compared with existing methods: the Chamfer distance value is reduced by about 2 times, the Earth Mover’s distance value is increased by 1.3 times, and the F1 value is increased by about 1.5 times. In addition, the effectiveness of the newly added modules is verified by ablation experiments, and the experimental results show that these modules play a key role in the generation process. Overall, the proposed model shows significant advantages in terms of accuracy and efficiency, especially in generating complete spatial point clouds.https://www.mdpi.com/2072-4292/17/1/153point cloud generationmultimodal3D point cloud map |
| spellingShingle | Wenwen Li Yaxing Chen Qianyue Fan Meng Yang Bin Guo Zhiwen Yu I-PAttnGAN: An Image-Assisted Point Cloud Generation Method Based on Attention Generative Adversarial Network Remote Sensing point cloud generation multimodal 3D point cloud map |
| title | I-PAttnGAN: An Image-Assisted Point Cloud Generation Method Based on Attention Generative Adversarial Network |
| title_full | I-PAttnGAN: An Image-Assisted Point Cloud Generation Method Based on Attention Generative Adversarial Network |
| title_fullStr | I-PAttnGAN: An Image-Assisted Point Cloud Generation Method Based on Attention Generative Adversarial Network |
| title_full_unstemmed | I-PAttnGAN: An Image-Assisted Point Cloud Generation Method Based on Attention Generative Adversarial Network |
| title_short | I-PAttnGAN: An Image-Assisted Point Cloud Generation Method Based on Attention Generative Adversarial Network |
| title_sort | i pattngan an image assisted point cloud generation method based on attention generative adversarial network |
| topic | point cloud generation multimodal 3D point cloud map |
| url | https://www.mdpi.com/2072-4292/17/1/153 |
| work_keys_str_mv | AT wenwenli ipattngananimageassistedpointcloudgenerationmethodbasedonattentiongenerativeadversarialnetwork AT yaxingchen ipattngananimageassistedpointcloudgenerationmethodbasedonattentiongenerativeadversarialnetwork AT qianyuefan ipattngananimageassistedpointcloudgenerationmethodbasedonattentiongenerativeadversarialnetwork AT mengyang ipattngananimageassistedpointcloudgenerationmethodbasedonattentiongenerativeadversarialnetwork AT binguo ipattngananimageassistedpointcloudgenerationmethodbasedonattentiongenerativeadversarialnetwork AT zhiwenyu ipattngananimageassistedpointcloudgenerationmethodbasedonattentiongenerativeadversarialnetwork |