SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929457731731456 |
|---|---|
| author | Liu, Yu Jia, Baoxiong Chen, Yixin Huang, Siyuan |
| author_facet | Liu, Yu Jia, Baoxiong Chen, Yixin Huang, Siyuan |
| contents | The ability to distill object-centric abstractions from intricate visual scenes underpins human-level generalization. Despite the significant progress in object-centric learning methods, learning object-centric representations in the 3D physical world remains a crucial challenge. In this work, we propose SlotLifter, a novel object-centric radiance model addressing scene reconstruction and decomposition jointly via slot-guided feature lifting. Such a design unites object-centric learning representations and image-based rendering methods, offering state-of-the-art performance in scene decomposition and novel-view synthesis on four challenging synthetic and four complex real-world datasets, outperforming existing 3D object-centric learning methods by a large margin. Through extensive ablative studies, we showcase the efficacy of designs in SlotLifter, revealing key insights for potential future directions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_06697 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields Liu, Yu Jia, Baoxiong Chen, Yixin Huang, Siyuan Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics The ability to distill object-centric abstractions from intricate visual scenes underpins human-level generalization. Despite the significant progress in object-centric learning methods, learning object-centric representations in the 3D physical world remains a crucial challenge. In this work, we propose SlotLifter, a novel object-centric radiance model addressing scene reconstruction and decomposition jointly via slot-guided feature lifting. Such a design unites object-centric learning representations and image-based rendering methods, offering state-of-the-art performance in scene decomposition and novel-view synthesis on four challenging synthetic and four complex real-world datasets, outperforming existing 3D object-centric learning methods by a large margin. Through extensive ablative studies, we showcase the efficacy of designs in SlotLifter, revealing key insights for potential future directions. |
| title | SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics |
| url | https://arxiv.org/abs/2408.06697 |