Efficient Semantic Splatting for Remote Sensing Multi-view Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qi, Zipeng, Chen, Hao, Zhang, Haotian, Zou, Zhengxia, Shi, Zhenwei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915060396326912
author Qi, Zipeng
Chen, Hao
Zhang, Haotian
Zou, Zhengxia
Shi, Zhenwei
author_facet Qi, Zipeng
Chen, Hao
Zhang, Haotian
Zou, Zhengxia
Shi, Zhenwei
contents In this paper, we propose a novel semantic splatting approach based on Gaussian Splatting to achieve efficient and low-latency. Our method projects the RGB attributes and semantic features of point clouds onto the image plane, simultaneously rendering RGB images and semantic segmentation results. Leveraging the explicit structure of point clouds and a one-time rendering strategy, our approach significantly enhances efficiency during optimization and rendering. Additionally, we employ SAM2 to generate pseudo-labels for boundary regions, which often lack sufficient supervision, and introduce two-level aggregation losses at the 2D feature map and 3D spatial levels to improve the view-consistent and spatial continuity.
format Preprint
id arxiv_https___arxiv_org_abs_2412_05969
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Semantic Splatting for Remote Sensing Multi-view Segmentation
Qi, Zipeng
Chen, Hao
Zhang, Haotian
Zou, Zhengxia
Shi, Zhenwei
Computer Vision and Pattern Recognition
In this paper, we propose a novel semantic splatting approach based on Gaussian Splatting to achieve efficient and low-latency. Our method projects the RGB attributes and semantic features of point clouds onto the image plane, simultaneously rendering RGB images and semantic segmentation results. Leveraging the explicit structure of point clouds and a one-time rendering strategy, our approach significantly enhances efficiency during optimization and rendering. Additionally, we employ SAM2 to generate pseudo-labels for boundary regions, which often lack sufficient supervision, and introduce two-level aggregation losses at the 2D feature map and 3D spatial levels to improve the view-consistent and spatial continuity.
title Efficient Semantic Splatting for Remote Sensing Multi-view Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.05969