SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields

Autor:	Liu, Yu, Jia, Baoxiong, Chen, Yixin, Huang, Siyuan
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence Computer Science - Machine Learning Computer Science - Robotics
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted by ECCV 2024. Project website: https://slotlifter.github.io
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2408.06697 Zobrazit plný text záznamu View this record from Arxiv