Real-Time Single Image Depth Perception in the Wild with Handheld Devices
| Autor: | Matteo Poggi, Filippo Aleotti, Giulio Zaccaroni, Luca Bartolomei, Fabio Tosi, Stefano Mattoccia |
|---|---|
| Přispěvatelé: | Aleotti, Filippo, Zaccaroni, Giulio, Bartolomei, Luca, Poggi, Matteo, Tosi, Fabio, Mattoccia, Stefano |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer science Reliability (computer networking) Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition monocular depth estimation 02 engineering and technology lcsh:Chemical technology smartphone 01 natural sciences Biochemistry Article Analytical Chemistry mobile system Computer Science - Graphics Human–computer interaction 0202 electrical engineering electronic engineering information engineering lcsh:TP1-1185 Electrical and Electronic Engineering Instrumentation mobile systems Monocular business.industry Deep learning 010401 analytical chemistry deep learning Atomic and Molecular Physics and Optics Graphics (cs.GR) 0104 chemical sciences Feature (computer vision) 020201 artificial intelligence & image processing Augmented reality Artificial intelligence Depth perception business Mobile device |
| Zdroj: | Sensors, Vol 21, Iss 15, p 15 (2021) Sensors (Basel, Switzerland) Sensors Volume 21 Issue 1 |
| Popis: | Depth perception is paramount to tackle real-world problems, ranging from autonomous driving to consumer applications. For the latter, depth estimation from a single image represents the most versatile solution, since a standard camera is available on almost any handheld device. Nonetheless, two main issues limit its practical deployment: i) the low reliability when deployed in-the-wild and ii) the demanding resource requirements to achieve real-time performance, often not compatible with such devices. Therefore, in this paper, we deeply investigate these issues showing how they are both addressable adopting appropriate network design and training strategies -- also outlining how to map the resulting networks on handheld devices to achieve real-time performance. Our thorough evaluation highlights the ability of such fast networks to generalize well to new environments, a crucial feature required to tackle the extremely varied contexts faced in real applications. Indeed, to further support this evidence, we report experimental results concerning real-time depth-aware augmented reality and image blurring with smartphones in-the-wild. Comment: 11 pages, 9 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|