ActiveGAMER: Active GAussian Mapping through Efficient Rendering

2025-01-12

AI Summary

To address inefficiency, insufficient information acquisition, and inadequate map completeness and fidelity in active scene mapping within complex environments, this work pioneers the integration of 3D Gaussian Splatting (3DGS) into an active scene mapping framework. We propose a rendering-driven information gain evaluation mechanism that jointly optimizes geometric and photometric fidelity; design a coarse-to-fine exploration strategy, a post-optimization reconstruction module, and a global-local collaborative keyframe selection mechanism—collectively forming a closed-loop autonomous exploration and reconstruction system. Evaluated on the Replica and Matterport3D (MP3D) datasets, our method achieves significant improvements in map completeness, geometric accuracy, and photometric fidelity, establishing new state-of-the-art (SOTA) performance across all major metrics.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

We introduce ActiveGAMER, an active mapping system that utilizes 3D Gaussian Splatting (3DGS) to achieve high-quality, real-time scene mapping and exploration. Unlike traditional NeRF-based methods, which are computationally demanding and restrict active mapping performance, our approach leverages the efficient rendering capabilities of 3DGS, allowing effective and efficient exploration in complex environments. The core of our system is a rendering-based information gain module that dynamically identifies the most informative viewpoints for next-best-view planning, enhancing both geometric and photometric reconstruction accuracy. ActiveGAMER also integrates a carefully balanced framework, combining coarse-to-fine exploration, post-refinement, and a global-local keyframe selection strategy to maximize reconstruction completeness and fidelity. Our system autonomously explores and reconstructs environments with state-of-the-art geometric and photometric accuracy and completeness, significantly surpassing existing approaches in both aspects. Extensive evaluations on benchmark datasets such as Replica and MP3D highlight ActiveGAMER's effectiveness in active mapping tasks.

Problem

• Environmental Mapping
• Complex Environments
• Map Precision and Completeness

Innovation

• 3D Graphics Technology
• Intelligent Visual Assessment
• Autonomous Environment Exploration