SlotLifter: Slot-Guided Feature Lifting for Learning Object-Centric Radiance Fields
Abstract
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 , 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 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 , revealing key insights for potential future directions.
Cite
Text
Liu et al. "SlotLifter: Slot-Guided Feature Lifting for Learning Object-Centric Radiance Fields." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72673-6_15Markdown
[Liu et al. "SlotLifter: Slot-Guided Feature Lifting for Learning Object-Centric Radiance Fields." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/liu2024eccv-slotlifter/) doi:10.1007/978-3-031-72673-6_15BibTeX
@inproceedings{liu2024eccv-slotlifter,
title = {{SlotLifter: Slot-Guided Feature Lifting for Learning Object-Centric Radiance Fields}},
author = {Liu, Yu and Jia, Baoxiong and Chen, Yixin and Huang, Siyuan},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-72673-6_15},
url = {https://mlanthology.org/eccv/2024/liu2024eccv-slotlifter/}
}