3DInFoGAN : 3D models’ reconstruction in InFoGANS
In computer vision and computer graphics, 3D reconstruction is the process of capturing real objects’ shapes and appearances. 3D models always can be constructed by active methods which use high-quality scanner equipment, or passive methods that learn from the dataset. However, both of these two met...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit Universiti Kebangsaan Malaysia
2021
|
| Online Access: | http://journalarticle.ukm.my/17959/ http://journalarticle.ukm.my/17959/1/07.pdf |
| _version_ | 1848814445511311360 |
|---|---|
| author | Du, Chunqi Hasegawa, Shinobu |
| author_facet | Du, Chunqi Hasegawa, Shinobu |
| author_sort | Du, Chunqi |
| building | UKM Institutional Repository |
| collection | Online Access |
| description | In computer vision and computer graphics, 3D reconstruction is the process of capturing real objects’ shapes and appearances. 3D models always can be constructed by active methods which use high-quality scanner equipment, or passive methods that learn from the dataset. However, both of these two methods only aimed to construct the 3D models, without showing what element affects the generation of 3D models. Therefore, the goal of this research is to apply deep learning to automatically generating 3D models, and finding the latent variables which affect the reconstructing process. The existing research GANs can be trained in little data with two networks called Generator and Discriminator, respectively. Generator can produce synthetic data, and Discriminator can discriminate between the generator’s output and real data. The existing research shows that InFoGAN can maximize the mutual information between latent variables and observation. In our approach, we will generate the 3D models based on InFoGAN and design two constraints, shape-constraint and parameters-constraint, respectively. Shape-constraint utilizes the data augmentation method to limit the synthetic data generated in the models’ profiles. At the same time, we also try to employ parameters-constraint to find the 3D models’ relationship corresponding to the latent variables. Furthermore, our approach will be a challenge in the architecture of generating 3D models built on InFoGAN. Finally, in the process of generation, we might discover the contribution of the latent variables influencing the 3D models to the whole network. |
| first_indexed | 2025-11-15T00:34:12Z |
| format | Article |
| id | oai:generic.eprints.org:17959 |
| institution | Universiti Kebangasaan Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T00:34:12Z |
| publishDate | 2021 |
| publisher | Penerbit Universiti Kebangsaan Malaysia |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | oai:generic.eprints.org:179592022-01-15T08:16:16Z http://journalarticle.ukm.my/17959/ 3DInFoGAN : 3D models’ reconstruction in InFoGANS Du, Chunqi Hasegawa, Shinobu In computer vision and computer graphics, 3D reconstruction is the process of capturing real objects’ shapes and appearances. 3D models always can be constructed by active methods which use high-quality scanner equipment, or passive methods that learn from the dataset. However, both of these two methods only aimed to construct the 3D models, without showing what element affects the generation of 3D models. Therefore, the goal of this research is to apply deep learning to automatically generating 3D models, and finding the latent variables which affect the reconstructing process. The existing research GANs can be trained in little data with two networks called Generator and Discriminator, respectively. Generator can produce synthetic data, and Discriminator can discriminate between the generator’s output and real data. The existing research shows that InFoGAN can maximize the mutual information between latent variables and observation. In our approach, we will generate the 3D models based on InFoGAN and design two constraints, shape-constraint and parameters-constraint, respectively. Shape-constraint utilizes the data augmentation method to limit the synthetic data generated in the models’ profiles. At the same time, we also try to employ parameters-constraint to find the 3D models’ relationship corresponding to the latent variables. Furthermore, our approach will be a challenge in the architecture of generating 3D models built on InFoGAN. Finally, in the process of generation, we might discover the contribution of the latent variables influencing the 3D models to the whole network. Penerbit Universiti Kebangsaan Malaysia 2021-12 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/17959/1/07.pdf Du, Chunqi and Hasegawa, Shinobu (2021) 3DInFoGAN : 3D models’ reconstruction in InFoGANS. Asia-Pacific Journal of Information Technology and Multimedia, 10 (2). pp. 95-109. ISSN 2289-2192 https://www.ukm.my/apjitm/articles-year.php |
| spellingShingle | Du, Chunqi Hasegawa, Shinobu 3DInFoGAN : 3D models’ reconstruction in InFoGANS |
| title | 3DInFoGAN : 3D models’ reconstruction in InFoGANS |
| title_full | 3DInFoGAN : 3D models’ reconstruction in InFoGANS |
| title_fullStr | 3DInFoGAN : 3D models’ reconstruction in InFoGANS |
| title_full_unstemmed | 3DInFoGAN : 3D models’ reconstruction in InFoGANS |
| title_short | 3DInFoGAN : 3D models’ reconstruction in InFoGANS |
| title_sort | 3dinfogan : 3d models’ reconstruction in infogans |
| url | http://journalarticle.ukm.my/17959/ http://journalarticle.ukm.my/17959/ http://journalarticle.ukm.my/17959/1/07.pdf |