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...
Main Authors: | Bhalgat, Y, Laina, I, Henriques, JF, Zisserman, A, Vedaldi, A |
---|---|
格式: | Conference item |
語言: | English |
出版: |
Curran Associates
2024
|
相似書籍
-
3D-aware instance segmentation and tracking in egocentric videos
由: Bhalgat, Y, et al.
出版: (2025) -
Instance Segmentation of Shrimp Based on Contrastive Learning
由: Heng Zhou, et al.
出版: (2023-06-01) -
N2F2: hierarchical scene understanding with nested neural feature fields
由: Bhalgat, YS, et al.
出版: (2024) -
Instance-Level Contrastive Learning for Weakly Supervised Object Detection
由: Ming Zhang, et al.
出版: (2022-10-01) -
Unsupervised part discovery from contrastive reconstruction
由: Choudhury, S, et al.
出版: (2021)