Gaussian Mapping for Evolving Scenes

TL;DR

This paper introduces Gaussian Mapping for Evolving Scenes (GaME), a method that dynamically updates 3D Gaussian Splatting to handle scene changes over time, improving reconstruction accuracy in dynamic environments.

Contribution

It presents a novel dynamic scene adaptation and keyframe management mechanism for 3D Gaussian Splatting, addressing long-term scene evolution challenges.

Findings

Achieved 29.7% improvement in PSNR over baseline.

Threefold reduction in L1 depth error.

Validated on synthetic and real-world datasets.

Abstract

Mapping systems with novel view synthesis (NVS) capabilities, most notably 3D Gaussian Splatting (3DGS), are widely used in computer vision, as well as in various applications, including augmented reality, robotics, and autonomous driving. However, many current approaches are limited to static scenes. While recent works have begun addressing short-term dynamics (motion within the camera's view), long-term dynamics (the scene evolving through changes out of view) remain less explored. To overcome this limitation, we introduce a dynamic scene adaptation mechanism to continuously update 3DGS to reflect the latest changes. Since maintaining consistency remains challenging due to stale observations disrupting the reconstruction process, we further propose a novel keyframe management mechanism that discards outdated observations while preserving as much information as possible. We thoroughly evaluate Gaussian Mapping for Evolving Scenes (GaME) on both synthetic and real-world datasets, achieving a 29.7% improvement in PSNR and a 3 times improvement in L1 depth error over the most competitive baseline.