Multi-view Remote Sensing Image Segmentation With SAM priors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qi, Zipeng, Liu, Chenyang, Liu, Zili, Chen, Hao, Wu, Yongchang, Zou, Zhengxia, Sh, Zhenwei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913359680503808
author Qi, Zipeng
Liu, Chenyang
Liu, Zili
Chen, Hao
Wu, Yongchang
Zou, Zhengxia
Sh, Zhenwei
author_facet Qi, Zipeng
Liu, Chenyang
Liu, Zili
Chen, Hao
Wu, Yongchang
Zou, Zhengxia
Sh, Zhenwei
contents Multi-view segmentation in Remote Sensing (RS) seeks to segment images from diverse perspectives within a scene. Recent methods leverage 3D information extracted from an Implicit Neural Field (INF), bolstering result consistency across multiple views while using limited accounts of labels (even within 3-5 labels) to streamline labor. Nonetheless, achieving superior performance within the constraints of limited-view labels remains challenging due to inadequate scene-wide supervision and insufficient semantic features within the INF. To address these. we propose to inject the prior of the visual foundation model-Segment Anything(SAM), to the INF to obtain better results under the limited number of training data. Specifically, we contrast SAM features between testing and training views to derive pseudo labels for each testing view, augmenting scene-wide labeling information. Subsequently, we introduce SAM features via a transformer into the INF of the scene, supplementing the semantic information. The experimental results demonstrate that our method outperforms the mainstream method, confirming the efficacy of SAM as a supplement to the INF for this task.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14171
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-view Remote Sensing Image Segmentation With SAM priors
Qi, Zipeng
Liu, Chenyang
Liu, Zili
Chen, Hao
Wu, Yongchang
Zou, Zhengxia
Sh, Zhenwei
Computer Vision and Pattern Recognition
Multi-view segmentation in Remote Sensing (RS) seeks to segment images from diverse perspectives within a scene. Recent methods leverage 3D information extracted from an Implicit Neural Field (INF), bolstering result consistency across multiple views while using limited accounts of labels (even within 3-5 labels) to streamline labor. Nonetheless, achieving superior performance within the constraints of limited-view labels remains challenging due to inadequate scene-wide supervision and insufficient semantic features within the INF. To address these. we propose to inject the prior of the visual foundation model-Segment Anything(SAM), to the INF to obtain better results under the limited number of training data. Specifically, we contrast SAM features between testing and training views to derive pseudo labels for each testing view, augmenting scene-wide labeling information. Subsequently, we introduce SAM features via a transformer into the INF of the scene, supplementing the semantic information. The experimental results demonstrate that our method outperforms the mainstream method, confirming the efficacy of SAM as a supplement to the INF for this task.
title Multi-view Remote Sensing Image Segmentation With SAM priors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.14171