Contrastive lift: 3D object instance segmentation by slow-fast contrastive fusion
Instance segmentation in 3D is a challenging task due to the lack of large-scale annotated datasets. In this paper, we show that this task can be addressed effectively by leveraging instead 2D pre-trained models for instance segmentation. We propose a novel approach to lift 2D segments to 3D and fus...
Główni autorzy: | Bhalgat, Y, Laina, I, Henriques, JF, Zisserman, A, Vedaldi, A |
---|---|
Format: | Conference item |
Język: | English |
Wydane: |
Curran Associates
2024
|
Podobne zapisy
-
3D-aware instance segmentation and tracking in egocentric videos
od: Bhalgat, Y, i wsp.
Wydane: (2025) -
Instance Segmentation of Shrimp Based on Contrastive Learning
od: Heng Zhou, i wsp.
Wydane: (2023-06-01) -
N2F2: hierarchical scene understanding with nested neural feature fields
od: Bhalgat, YS, i wsp.
Wydane: (2024) -
Instance-Level Contrastive Learning for Weakly Supervised Object Detection
od: Ming Zhang, i wsp.
Wydane: (2022-10-01) -
Unsupervised part discovery from contrastive reconstruction
od: Choudhury, S, i wsp.
Wydane: (2021)