cs.CVNov 16, 2026

InterRSGaussian: Interactive Multi-view Instance Segmentation for 3D Remote Sensing Scenes

Authors: Zipeng Qi, Zhengxia Zou, Zhenwei Shi

Organizations: School of Astronautics, Beihang University, Beijing, 100191, China · Key Laboratory of Spacecraft Design Optimization and Dynamic Simulation Technologies, Ministry of Education, Beihang University, Beijing, 100191, China

Abstract

Remote sensing image segmentation plays a critical role in various applications. Interactive instance segmentation, a specialized task within image segmentation, aims to generate precise segmentation results for target objects based on user input prompts. However, previous studies on interactive instance segmentation primarily focus on single-view images, limiting their ability to comprehensively understand complex 3D remote sensing scenes. In this study, we extend interactive instance segmentation from a single-view to a multi-view framework, which can also be easily converted to a 3D segmentation format, thus achieving more accurate and comprehensive 3D remote sensing scene perception across multiple views. First, we construct a multi-view interactive instance segmentation dataset for remote sensing, comprising five distinct scenes, each captured from about one hundred different views. Second, we propose InterRSGaussian, a novel instance segmentation method based on 3D Gaussians. InterRSGaussian enables users to provide point clicks on target objects from any arbitrary view and generates view-consistent instance segmentation results across all input views without requiring manual annotations. The resulting multi-view segmentation can further be projected onto 3D point clouds for 3D segmentation. To improve training efficiency and segmentation performance, we introduce a prior distillation network for initialization. Overall, this study extends traditional 2D remote sensing scene perception into a 3D multi-view framework, enabling a more comprehensive understanding of target objects in complex environments with user interactivity.

Figures & tables

Explore similar work

CardsList
  1. ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings

    May 9, 2026Xueyang Kang, Zijian Yu, Kourosh Khoshelham +13D Point Cloud Segmentation3D Instance Segmentation

  2. Consistent Scene Understanding in 3D Gaussian Splatting via Multi-Cue Mask Refinement

    Jul 2, 2026Hyunjoon Park, Donghyeon ChoMulti-View Consistency3D Gaussian Splatting

  3. PointGauss: Point Cloud-Guided Multi-Object Segmentation for Gaussian Splatting

    Aug 1, 2025Wentao Sun, Yiping Chen, John S. Zelek +13D Gaussian Splatting3DGS Segmentation