R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911802866008064 |
|---|---|
| author | Wu, Qirui Raychaudhuri, Sonia Ritchie, Daniel Savva, Manolis Chang, Angel X |
| author_facet | Wu, Qirui Raychaudhuri, Sonia Ritchie, Daniel Savva, Manolis Chang, Angel X |
| contents | We introduce the Reality-linked 3D Scenes (R3DS) dataset of synthetic 3D scenes mirroring the real-world scene arrangements from Matterport3D panoramas. Compared to prior work, R3DS has more complete and densely populated scenes with objects linked to real-world observations in panoramas. R3DS also provides an object support hierarchy, and matching object sets (e.g., same chairs around a dining table) for each scene. Overall, R3DS contains 19K objects represented by 3,784 distinct CAD models from over 100 object categories. We demonstrate the effectiveness of R3DS on the Panoramic Scene Understanding task. We find that: 1) training on R3DS enables better generalization; 2) support relation prediction trained with R3DS improves performance compared to heuristically calculated support; and 3) R3DS offers a challenging benchmark for future work on panoramic scene understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12301 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding Wu, Qirui Raychaudhuri, Sonia Ritchie, Daniel Savva, Manolis Chang, Angel X Computer Vision and Pattern Recognition We introduce the Reality-linked 3D Scenes (R3DS) dataset of synthetic 3D scenes mirroring the real-world scene arrangements from Matterport3D panoramas. Compared to prior work, R3DS has more complete and densely populated scenes with objects linked to real-world observations in panoramas. R3DS also provides an object support hierarchy, and matching object sets (e.g., same chairs around a dining table) for each scene. Overall, R3DS contains 19K objects represented by 3,784 distinct CAD models from over 100 object categories. We demonstrate the effectiveness of R3DS on the Panoramic Scene Understanding task. We find that: 1) training on R3DS enables better generalization; 2) support relation prediction trained with R3DS improves performance compared to heuristically calculated support; and 3) R3DS offers a challenging benchmark for future work on panoramic scene understanding. |
| title | R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.12301 |