Deep Models for Multi-View 3D Object Recognition: A Review
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914064335110144 |
|---|---|
| author | Alzahrani, Mona Usman, Muhammad Kammoun, Salma Anwar, Saeed Helmy, Tarek |
| author_facet | Alzahrani, Mona Usman, Muhammad Kammoun, Salma Anwar, Saeed Helmy, Tarek |
| contents | Human decision-making often relies on visual information from multiple perspectives or views. In contrast, machine learning-based object recognition utilizes information from a single image of the object. However, the information conveyed by a single image may not be sufficient for accurate decision-making, particularly in complex recognition problems. The utilization of multi-view 3D representations for object recognition has thus far demonstrated the most promising results for achieving state-of-the-art performance. This review paper comprehensively covers recent progress in multi-view 3D object recognition methods for 3D classification and retrieval tasks. Specifically, we focus on deep learning-based and transformer-based techniques, as they are widely utilized and have achieved state-of-the-art performance. We provide detailed information about existing deep learning-based and transformer-based multi-view 3D object recognition models, including the most commonly used 3D datasets, camera configurations and number of views, view selection strategies, pre-trained CNN architectures, fusion strategies, and recognition performance on 3D classification and 3D retrieval tasks. Additionally, we examine various computer vision applications that use multi-view classification. Finally, we highlight key findings and future directions for developing multi-view 3D object recognition methods to provide readers with a comprehensive understanding of the field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15224 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep Models for Multi-View 3D Object Recognition: A Review Alzahrani, Mona Usman, Muhammad Kammoun, Salma Anwar, Saeed Helmy, Tarek Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Human decision-making often relies on visual information from multiple perspectives or views. In contrast, machine learning-based object recognition utilizes information from a single image of the object. However, the information conveyed by a single image may not be sufficient for accurate decision-making, particularly in complex recognition problems. The utilization of multi-view 3D representations for object recognition has thus far demonstrated the most promising results for achieving state-of-the-art performance. This review paper comprehensively covers recent progress in multi-view 3D object recognition methods for 3D classification and retrieval tasks. Specifically, we focus on deep learning-based and transformer-based techniques, as they are widely utilized and have achieved state-of-the-art performance. We provide detailed information about existing deep learning-based and transformer-based multi-view 3D object recognition models, including the most commonly used 3D datasets, camera configurations and number of views, view selection strategies, pre-trained CNN architectures, fusion strategies, and recognition performance on 3D classification and 3D retrieval tasks. Additionally, we examine various computer vision applications that use multi-view classification. Finally, we highlight key findings and future directions for developing multi-view 3D object recognition methods to provide readers with a comprehensive understanding of the field. |
| title | Deep Models for Multi-View 3D Object Recognition: A Review |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2404.15224 |