Multi-View Pose-Agnostic Change Localization with Zero Labels
원문 초록
Autonomous agents often require accurate methods for detecting and localizing changes in their environment, particularly when observations are captured from unconstrained and inconsistent viewpoints. We propose a novel label-free, pose-agnostic change detection method that integrates information from multiple viewpoints to construct a change-aware 3D Gaussian Splatting (3DGS) representation of the scene. With as few as 5 images of the post-change scene, our approach can learn additional change channels in a 3DGS and produce change masks that outperform single-view techniques. Our change-aware 3D scene representation additionally enables the generation of accurate change masks for unseen viewpoints. Experimental results demonstrate state-of-the-art performance in complex multi-object scenes, achieving a 1.7$\times$ and 1.6$\times$ improvement in Mean Intersection Over Union and F1 score respectively over other baselines. We also contribute a new real-world dataset to benchmark change detection in diverse challenging scenes in the presence of lighting variations.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
GS-LTS: 3D Gaussian Splatting-Based Adaptive Modeling for Long-Term Service Robots
Precision Spatio-Temporal Feature Fusion for Robust Remote Sensing Change Detection
Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices
R3eVision: A Survey on Robust Rendering, Restoration, and Enhancement for 3D Low-Level Vision
HydroChronos: Forecasting Decades of Surface Water Change
3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting
토론
이 논문과 연결된 포럼 글이 아직 없습니다.