Active scene reconstruction balances quality and speed with 2d gaussian splatting
2D GauSS-MI: Efficient Active Scene Reconstruction with Balanced Visual and Geometric Quality
Computer Vision and Pattern RecognitionRobotics
Summary
Reconstructing a 3D scene requires choosing the right camera views to get good pictures and shapes without using too much computing power. The authors created a new method that uses 2D Gaussian splatting, a way to represent surfaces, to quickly update a 3D model as new images arrive. They also designed a way to estimate how good each part of the model is and pick camera angles that improve both how the scene looks and how accurate its shapes are. Their tests show this method works well and faster than other recent approaches without needing much storage.
What this means in practice
- •For robotic navigation teams: Select efficient views for robot cameras to build accurate maps of environments in real time with limited computing resources.
- •For augmented reality developers: Improve 3D scene models used in AR by balancing appearance and shape accuracy while keeping reconstruction fast.
Authors
Yuhan Xie, Jia Pan
Abstract
Active reconstruction requires efficient active view selection to achieve high-quality reconstruction within limited onboard computational resources. Existing methods face challenges in adequately balancing visual and geometric quality with the computational efficiency required for real-time operation. In this work, we present an active reconstruction framework based on 2D Gaussian Splatting (2DGS). We develop an efficient online 2DGS mapping pipeline for incremental RGB-D observations and introduce a probabilistic reliability model that characterizes the view-dependent reconstruction quality of individual 2D Gaussian splats. Building on this model, we formulate 2D Gaussian Splatting Shannon Mutual Information (2D GauSS-MI), a mutual-information-based metric that exploits the explicit surface orientation of 2DGS to evaluate the expected information gain of candidate views. The proposed metric enables active view selection to account for both visual and geometric reconstruction quality. We evaluate the proposed system against three state-of-the-art baselines on eight Replica scenes. Experimental results demonstrate that our method achieves a favorable balance between visual and geometric reconstruction quality with substantially lower computational cost and competitive model storage.