3DCoMPaT$^{++}$: An improved Large-scale 3D Vision Dataset for Compositional Recognition
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908341290139648 |
|---|---|
| author | Slim, Habib Li, Xiang Li, Yuchen Ahmed, Mahmoud Ayman, Mohamed Upadhyay, Ujjwal Abdelreheem, Ahmed Prajapati, Arpit Pothigara, Suhail Wonka, Peter Elhoseiny, Mohamed |
| author_facet | Slim, Habib Li, Xiang Li, Yuchen Ahmed, Mahmoud Ayman, Mohamed Upadhyay, Ujjwal Abdelreheem, Ahmed Prajapati, Arpit Pothigara, Suhail Wonka, Peter Elhoseiny, Mohamed |
| contents | In this work, we present 3DCoMPaT$^{++}$, a multimodal 2D/3D dataset with 160 million rendered views of more than 10 million stylized 3D shapes carefully annotated at the part-instance level, alongside matching RGB point clouds, 3D textured meshes, depth maps, and segmentation masks. 3DCoMPaT$^{++}$ covers 41 shape categories, 275 fine-grained part categories, and 293 fine-grained material classes that can be compositionally applied to parts of 3D objects. We render a subset of one million stylized shapes from four equally spaced views as well as four randomized views, leading to a total of 160 million renderings. Parts are segmented at the instance level, with coarse-grained and fine-grained semantic levels. We introduce a new task, called Grounded CoMPaT Recognition (GCR), to collectively recognize and ground compositions of materials on parts of 3D objects. Additionally, we report the outcomes of a data challenge organized at CVPR2023, showcasing the winning method's utilization of a modified PointNet$^{++}$ model trained on 6D inputs, and exploring alternative techniques for GCR enhancement. We hope our work will help ease future research on compositional 3D Vision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_18511 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | 3DCoMPaT$^{++}$: An improved Large-scale 3D Vision Dataset for Compositional Recognition Slim, Habib Li, Xiang Li, Yuchen Ahmed, Mahmoud Ayman, Mohamed Upadhyay, Ujjwal Abdelreheem, Ahmed Prajapati, Arpit Pothigara, Suhail Wonka, Peter Elhoseiny, Mohamed Computer Vision and Pattern Recognition Artificial Intelligence In this work, we present 3DCoMPaT$^{++}$, a multimodal 2D/3D dataset with 160 million rendered views of more than 10 million stylized 3D shapes carefully annotated at the part-instance level, alongside matching RGB point clouds, 3D textured meshes, depth maps, and segmentation masks. 3DCoMPaT$^{++}$ covers 41 shape categories, 275 fine-grained part categories, and 293 fine-grained material classes that can be compositionally applied to parts of 3D objects. We render a subset of one million stylized shapes from four equally spaced views as well as four randomized views, leading to a total of 160 million renderings. Parts are segmented at the instance level, with coarse-grained and fine-grained semantic levels. We introduce a new task, called Grounded CoMPaT Recognition (GCR), to collectively recognize and ground compositions of materials on parts of 3D objects. Additionally, we report the outcomes of a data challenge organized at CVPR2023, showcasing the winning method's utilization of a modified PointNet$^{++}$ model trained on 6D inputs, and exploring alternative techniques for GCR enhancement. We hope our work will help ease future research on compositional 3D Vision. |
| title | 3DCoMPaT$^{++}$: An improved Large-scale 3D Vision Dataset for Compositional Recognition |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2310.18511 |