Processing math: 100%
Real-Time Self-Supervised Monocular Depth Estimation Without GPU | IEEE Journals & Magazine | IEEE Xplore

Real-Time Self-Supervised Monocular Depth Estimation Without GPU


Abstract:

Single-image depth estimation represents a longstanding challenge in computer vision and although it is an ill-posed problem, deep learning enabled astonishing results le...Show More

Abstract:

Single-image depth estimation represents a longstanding challenge in computer vision and although it is an ill-posed problem, deep learning enabled astonishing results leveraging both supervised and self-supervised training paradigms. State-of-the-art solutions achieve remarkably accurate depth estimation from a single image deploying huge deep architectures, requiring powerful dedicated hardware to run in a reasonable amount of time. This overly demanding complexity makes them unsuited for a broad category of applications requiring devices with constrained resources or memory consumption. To tackle this issue, in this paper a family of compact, yet effective CNNs for monocular depth estimation is proposed, by leveraging self-supervision from a binocular stereo rig. Our lightweight architectures, namely PyD-Net and PyD-Net2, compared to complex state-of-the-art trade a small drop in accuracy to drastically reduce the runtime and memory requirements by a factor ranging from 2\times to 100\times . Moreover, our networks can run real-time monocular depth estimation on a broad set of embedded or consumer devices, even not equipped with a GPU, by early stopping the inference with negligible (or no) loss in accuracy, making it ideally suited for real applications with strict constraints on hardware resources or power consumption.
Published in: IEEE Transactions on Intelligent Transportation Systems ( Volume: 23, Issue: 10, October 2022)
Page(s): 17342 - 17353
Date of Publication: 14 March 2022

ISSN Information:


Contact IEEE to Subscribe

References

References is not available for this document.