Details

Autor(en) / Beteiligte

• Poggi, Matteo
• Tosi, Fabio
• Aleotti, Filippo
• Mattoccia, Stefano

Titel

Real-Time Self-Supervised Monocular Depth Estimation Without GPU

Ist Teil von

• IEEE transactions on intelligent transportation systems, 2022-10, Vol.23 (10), p.17342-17353

Ort / Verlag

New York: IEEE

Erscheinungsjahr

2022

Quelle

IEEE/IET Electronic Library

Beschreibungen/Notizen

• 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 <inline-formula> <tex-math notation="LaTeX">2\times </tex-math></inline-formula> to <inline-formula> <tex-math notation="LaTeX">100\times </tex-math></inline-formula>. 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.