Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2403.18118 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911964588933120 |
|---|---|
| author | Gu, Qiao Lv, Zhaoyang Frost, Duncan Green, Simon Straub, Julian Sweeney, Chris |
| author_facet | Gu, Qiao Lv, Zhaoyang Frost, Duncan Green, Simon Straub, Julian Sweeney, Chris |
| contents | In this paper we present EgoLifter, a novel system that can automatically segment scenes captured from egocentric sensors into a complete decomposition of individual 3D objects. The system is specifically designed for egocentric data where scenes contain hundreds of objects captured from natural (non-scanning) motion. EgoLifter adopts 3D Gaussians as the underlying representation of 3D scenes and objects and uses segmentation masks from the Segment Anything Model (SAM) as weak supervision to learn flexible and promptable definitions of object instances free of any specific object taxonomy. To handle the challenge of dynamic objects in ego-centric videos, we design a transient prediction module that learns to filter out dynamic objects in the 3D reconstruction. The result is a fully automatic pipeline that is able to reconstruct 3D object instances as collections of 3D Gaussians that collectively compose the entire scene. We created a new benchmark on the Aria Digital Twin dataset that quantitatively demonstrates its state-of-the-art performance in open-world 3D segmentation from natural egocentric input. We run EgoLifter on various egocentric activity datasets which shows the promise of the method for 3D egocentric perception at scale. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_18118 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EgoLifter: Open-world 3D Segmentation for Egocentric Perception Gu, Qiao Lv, Zhaoyang Frost, Duncan Green, Simon Straub, Julian Sweeney, Chris Computer Vision and Pattern Recognition In this paper we present EgoLifter, a novel system that can automatically segment scenes captured from egocentric sensors into a complete decomposition of individual 3D objects. The system is specifically designed for egocentric data where scenes contain hundreds of objects captured from natural (non-scanning) motion. EgoLifter adopts 3D Gaussians as the underlying representation of 3D scenes and objects and uses segmentation masks from the Segment Anything Model (SAM) as weak supervision to learn flexible and promptable definitions of object instances free of any specific object taxonomy. To handle the challenge of dynamic objects in ego-centric videos, we design a transient prediction module that learns to filter out dynamic objects in the 3D reconstruction. The result is a fully automatic pipeline that is able to reconstruct 3D object instances as collections of 3D Gaussians that collectively compose the entire scene. We created a new benchmark on the Aria Digital Twin dataset that quantitatively demonstrates its state-of-the-art performance in open-world 3D segmentation from natural egocentric input. We run EgoLifter on various egocentric activity datasets which shows the promise of the method for 3D egocentric perception at scale. |
| title | EgoLifter: Open-world 3D Segmentation for Egocentric Perception |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.18118 |