DISORF: A Distributed Online 3D Reconstruction Framework for Mobile Robots
This addresses the challenge of real-time 3D scene reconstruction for mobile robots and edge devices with limited computing power, representing an incremental improvement in distributed systems for robotics.
The paper tackles the problem of enabling online 3D reconstruction on resource-constrained mobile robots by proposing DISORF, a distributed framework that splits computation between edge devices and remote servers, resulting in high-quality real-time reconstruction as demonstrated in experiments.
We present a framework, DISORF, to enable online 3D reconstruction and visualization of scenes captured by resource-constrained mobile robots and edge devices. To address the limited computing capabilities of edge devices and potentially limited network availability, we design a framework that efficiently distributes computation between the edge device and the remote server. We leverage on-device SLAM systems to generate posed keyframes and transmit them to remote servers that can perform high-quality 3D reconstruction and visualization at runtime by leveraging recent advances in neural 3D methods. We identify a key challenge with online training where naive image sampling strategies can lead to significant degradation in rendering quality. We propose a novel shifted exponential frame sampling method that addresses this challenge for online training. We demonstrate the effectiveness of our framework in enabling high-quality real-time reconstruction and visualization of unknown scenes as they are captured and streamed from cameras in mobile robots and edge devices.