RoutedFusion: Learning Real-time Depth Map Fusion
This work addresses the need for scalable and real-time depth fusion in 3D reconstruction, offering incremental improvements for applications like robotics and augmented reality.
The paper tackles the problem of real-time depth map fusion for 3D reconstruction by proposing a neural network-based method that predicts non-linear updates to reduce errors, outperforming traditional and learned approaches on synthetic and real data with improved handling of noise and outliers.
The efficient fusion of depth maps is a key part of most state-of-the-art 3D reconstruction methods. Besides requiring high accuracy, these depth fusion methods need to be scalable and real-time capable. To this end, we present a novel real-time capable machine learning-based method for depth map fusion. Similar to the seminal depth map fusion approach by Curless and Levoy, we only update a local group of voxels to ensure real-time capability. Instead of a simple linear fusion of depth information, we propose a neural network that predicts non-linear updates to better account for typical fusion errors. Our network is composed of a 2D depth routing network and a 3D depth fusion network which efficiently handle sensor-specific noise and outliers. This is especially useful for surface edges and thin objects for which the original approach suffers from thickening artifacts. Our method outperforms the traditional fusion approach and related learned approaches on both synthetic and real data. We demonstrate the performance of our method in reconstructing fine geometric details from noise and outlier contaminated data on various scenes.