Cross-Temporal 3D Gaussian Splatting for Sparse-View Guided Scene Update

TL;DR

This paper introduces Cross-Temporal 3D Gaussian Splatting, a framework for updating and reconstructing 3D scenes over time using sparse images and scene priors, enabling efficient scene versioning and temporal change detection.

Contribution

The paper presents a novel cross-temporal 3D Gaussian Splatting framework that allows scene updates and reconstructions from sparse views across different time periods, incorporating camera alignment and confidence-guided optimization.

Findings

Significant improvements in reconstruction quality over baselines.

Effective scene updating with sparse images and historical priors.

Supports non-continuous capture for temporal scene analysis.

Abstract

Maintaining consistent 3D scene representations over time is a significant challenge in computer vision. Updating 3D scenes from sparse-view observations is crucial for various real-world applications, including urban planning, disaster assessment, and historical site preservation, where dense scans are often unavailable or impractical. In this paper, we propose Cross-Temporal 3D Gaussian Splatting (Cross-Temporal 3DGS), a novel framework for efficiently reconstructing and updating 3D scenes across different time periods, using sparse images and previously captured scene priors. Our approach comprises three stages: 1) Cross-temporal camera alignment for estimating and aligning camera poses across different timestamps; 2) Interference-based confidence initialization to identify unchanged regions between timestamps, thereby guiding updates; and 3) Progressive cross-temporal optimization, which iteratively integrates historical prior information into the 3D scene to enhance reconstruction quality. Our method supports non-continuous capture, enabling not only updates using new sparse views to refine existing scenes, but also recovering past scenes from limited data with the help of current captures. Furthermore, we demonstrate the potential of this approach to achieve temporal changes using only sparse images, which can later be reconstructed into detailed 3D representations as needed. Experimental results show significant improvements over baseline methods in reconstruction quality and data efficiency, making this approach a promising solution for scene versioning, cross-temporal digital twins, and long-term spatial documentation.