Towards Real-time Video Compressive Sensing on Mobile Devices
Miao Cao, Lishun Wang, Huan Wang, Guoqing Wang, Xin Yuan

TL;DR
This paper introduces MobileSCI, a novel mobile-friendly video compressive sensing reconstruction model that achieves real-time high-quality video reconstruction on mobile devices like the iPhone 15, addressing previous computational challenges.
Contribution
MobileSCI is the first model designed for real-time video SCI reconstruction on mobile devices, utilizing an efficient U-shaped architecture and a novel feature mixing block.
Findings
Real-time reconstruction at 35 FPS on iPhone 15
Superior reconstruction quality on simulated and real data
Efficient architecture suitable for mobile deployment
Abstract
Video Snapshot Compressive Imaging (SCI) uses a low-speed 2D camera to capture high-speed scenes as snapshot compressed measurements, followed by a reconstruction algorithm to retrieve the high-speed video frames. The fast evolving mobile devices and existing high-performance video SCI reconstruction algorithms motivate us to develop mobile reconstruction methods for real-world applications. Yet, it is still challenging to deploy previous reconstruction algorithms on mobile devices due to the complex inference process, let alone real-time mobile reconstruction. To the best of our knowledge, there is no video SCI reconstruction model designed to run on the mobile devices. Towards this end, in this paper, we present an effective approach for video SCI reconstruction, dubbed MobileSCI, which can run at real-time speed on the mobile devices for the first time. Specifically, we first build a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSparse and Compressive Sensing Techniques · Energy Efficient Wireless Sensor Networks · Non-Invasive Vital Sign Monitoring
MethodsSPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings · Knowledge Distillation
