TY - GEN
T1 - SAPCGAN
T2 - 19th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2020
AU - Li, Yushi
AU - Baciu, George
N1 - Publisher Copyright:
©2020 IEEE
PY - 2020/9/26
Y1 - 2020/9/26
N2 - The direct extension of 2D image learning to three-dimensional space is 3D point cloud learning. Recently, point cloud learning has shown significant results in 3D shape estimation and semantic segmentation. Despite these advancements, fundamental problems in point cloud learning still pose significant challenges. These problems include representation learning, shape generation, shape segmentation, and shape matching. In this paper, we propose a cognitive self-attention based learning approach to aggregate global representation of 3D shapes from point cloud data. We also integrate 3D point data with a binary tree structure to build a point cloud generator. We further design a novel Generative Adversarial Network (GAN) architecture to generate point clouds resembling the ground truth that could be used for unsupervised learning of 3D shapes. Relying on a self-attention mechanism, our framework, called SAPCGAN, aggregates the global graph features to correct the structural information of 3D shapes in the latent space. Finally, we compare the performance of two gradient penalty methods used in stabilizing the training of our GAN system. We show that our framework has high training efficiency and can provide state-of-the-art results in 3D point cloud generation. The performance of our is demonstrated with both quantitative and qualitative experimental evaluations. Furthermore, the generated 3D point clouds can be segmented into their natural semantic parts, such as, for example the four legs of a chair, the wings of an air plane, or the four wheels of a car.
AB - The direct extension of 2D image learning to three-dimensional space is 3D point cloud learning. Recently, point cloud learning has shown significant results in 3D shape estimation and semantic segmentation. Despite these advancements, fundamental problems in point cloud learning still pose significant challenges. These problems include representation learning, shape generation, shape segmentation, and shape matching. In this paper, we propose a cognitive self-attention based learning approach to aggregate global representation of 3D shapes from point cloud data. We also integrate 3D point data with a binary tree structure to build a point cloud generator. We further design a novel Generative Adversarial Network (GAN) architecture to generate point clouds resembling the ground truth that could be used for unsupervised learning of 3D shapes. Relying on a self-attention mechanism, our framework, called SAPCGAN, aggregates the global graph features to correct the structural information of 3D shapes in the latent space. Finally, we compare the performance of two gradient penalty methods used in stabilizing the training of our GAN system. We show that our framework has high training efficiency and can provide state-of-the-art results in 3D point cloud generation. The performance of our is demonstrated with both quantitative and qualitative experimental evaluations. Furthermore, the generated 3D point clouds can be segmented into their natural semantic parts, such as, for example the four legs of a chair, the wings of an air plane, or the four wheels of a car.
UR - http://www.scopus.com/inward/record.url?scp=85112866633&partnerID=8YFLogxK
U2 - 10.1109/ICCICC50026.2020.09450255
DO - 10.1109/ICCICC50026.2020.09450255
M3 - Conference Proceeding
AN - SCOPUS:85112866633
T3 - Proceedings of 2020 IEEE 19th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2020
SP - 52
EP - 59
BT - Proceedings of 2020 IEEE 19th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2020
A2 - Wang, Yingxu
A2 - Ge, Ning
A2 - Lu, Jianhua
A2 - Tao, Xiaoming
A2 - Soda, Paolo
A2 - Howard, Newton
A2 - Widrow, Bernard
A2 - Feldman, Jerome
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 26 September 2020 through 28 September 2020
ER -