VoxDepth: Rectification of Depth Images on Edge Devices

TL;DR

VoxDepth is a fast, accurate depth image rectification method designed for edge devices, utilizing 3D point cloud fusion to improve quality significantly over existing techniques without heavy computational demands.

Contribution

The paper introduces VoxDepth, a novel non-ML approach that combines 3D point cloud fusion and template creation for real-time depth image correction on resource-limited devices.

Findings

31% improvement in depth quality over state-of-the-art methods

Operates at 27 FPS on edge devices

Effective on both synthetic and real-world datasets

Abstract

Autonomous mobile robots like self-flying drones and industrial robots heavily depend on depth images to perform tasks such as 3D reconstruction and visual SLAM. However, the presence of inaccuracies in these depth images can greatly hinder the effectiveness of these applications, resulting in sub-optimal results. Depth images produced by commercially available cameras frequently exhibit noise, which manifests as flickering pixels and erroneous patches. ML-based methods to rectify these images are unsuitable for edge devices that have very limited computational resources. Non-ML methods are much faster but have limited accuracy, especially for correcting errors that are a result of occlusion and camera movement. We propose a scheme called VoxDepth that is fast, accurate, and runs very well on edge devices. It relies on a host of novel techniques: 3D point cloud construction and fusion, and using it to create a template that can fix erroneous depth images. VoxDepth shows superior results on both synthetic and real-world datasets. We demonstrate a 31% improvement in quality as compared to state-of-the-art methods on real-world depth datasets, while maintaining a competitive framerate of 27 FPS (frames per second).