English

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

Computer Vision and Pattern Recognition 2024-08-14 v1 Artificial Intelligence Machine Learning Robotics

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 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.

Keywords

Cite

@article{arxiv.2408.06697,
  title  = {SlotLifter: Slot-guided Feature Lifting for Learning Object-centric Radiance Fields},
  author = {Yu Liu and Baoxiong Jia and Yixin Chen and Siyuan Huang},
  journal= {arXiv preprint arXiv:2408.06697},
  year   = {2024}
}

Comments

Accepted by ECCV 2024. Project website: https://slotlifter.github.io

R2 v1 2026-06-28T18:11:24.918Z