Answerability Fields: Answerable Location Estimation via Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914888270479360 |
|---|---|
| author | Azuma, Daichi Miyanishi, Taiki Kurita, Shuhei Sakamoto, Koya Kawanabe, Motoaki |
| author_facet | Azuma, Daichi Miyanishi, Taiki Kurita, Shuhei Sakamoto, Koya Kawanabe, Motoaki |
| contents | In an era characterized by advancements in artificial intelligence and robotics, enabling machines to interact with and understand their environment is a critical research endeavor. In this paper, we propose Answerability Fields, a novel approach to predicting answerability within complex indoor environments. Leveraging a 3D question answering dataset, we construct a comprehensive Answerability Fields dataset, encompassing diverse scenes and questions from ScanNet. Using a diffusion model, we successfully infer and evaluate these Answerability Fields, demonstrating the importance of objects and their locations in answering questions within a scene. Our results showcase the efficacy of Answerability Fields in guiding scene-understanding tasks, laying the foundation for their application in enhancing interactions between intelligent agents and their environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_18497 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Answerability Fields: Answerable Location Estimation via Diffusion Models Azuma, Daichi Miyanishi, Taiki Kurita, Shuhei Sakamoto, Koya Kawanabe, Motoaki Computer Vision and Pattern Recognition In an era characterized by advancements in artificial intelligence and robotics, enabling machines to interact with and understand their environment is a critical research endeavor. In this paper, we propose Answerability Fields, a novel approach to predicting answerability within complex indoor environments. Leveraging a 3D question answering dataset, we construct a comprehensive Answerability Fields dataset, encompassing diverse scenes and questions from ScanNet. Using a diffusion model, we successfully infer and evaluate these Answerability Fields, demonstrating the importance of objects and their locations in answering questions within a scene. Our results showcase the efficacy of Answerability Fields in guiding scene-understanding tasks, laying the foundation for their application in enhancing interactions between intelligent agents and their environments. |
| title | Answerability Fields: Answerable Location Estimation via Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.18497 |