Filters








18,095 Hits in 9.1 sec

Measuring Distance with Mobile Phones Using Single-Camera Stereo Vision

Clemens Holzmann, Matthias Hochgatterer
2012 2012 32nd International Conference on Distributed Computing Systems Workshops  
In this paper, we present a solution for mobile devices with just one camera, which is a first step towards making computer stereo vision available to a wide range of devices that are not equipped with  ...  Computer stereo vision is an important technique for robotic navigation and other mobile scenarios where depth perception is needed, but it usually requires two cameras with a known horizontal displacement  ...  Second, we wanted to find out whether bigger baselines lead to more accurate distance estimations or not.  ... 
doi:10.1109/icdcsw.2012.22 dblp:conf/icdcsw/HolzmannH12 fatcat:yorrxfufircg7a4bsdxrdtxg6u

Mime

Andrea Colaço, Ahmed Kirmani, Hye Soo Yang, Nan-Wei Gong, Chris Schmandt, Vivek K. Goyal
2013 Proceedings of the 26th annual ACM symposium on User interface software and technology - UIST '13  
We demonstrate the utility of the Mime sensor for HMD interaction with a variety of application scenarios, including 3D spatial input using close-range gestures, gaming, on-the-move interaction, and operation  ...  Compared with state-of-the-art 3D sensors like TOF cameras, the Microsoft Kinect and the Leap Motion Controller, Mime offers several key advantages for mobile applications and HMD use cases: very small  ...  Acknowledgements: This material is based upon work supported in part by the National Science Foundation under Grant No. 1161413 and a Qualcomm Innovation Fellowship.  ... 
doi:10.1145/2501988.2502042 dblp:conf/uist/ColacoKYGSG13 fatcat:lr24tlrj2ndyvo5pz5gnn2v5am

Fast and Accurate: Video Enhancement using Sparse Depth [article]

Yu Feng, Patrick Hansen, Paul N. Whatmough, Guoyu Lu, Yuhao Zhu
2021 arXiv   pre-print
This paper presents a general framework to build fast and accurate algorithms for video enhancement tasks such as super-resolution, deblurring, and denoising.  ...  Building on top of the flow estimation, we demonstrate a general framework that integrates the flows in a plug-and-play fashion with different task-specific layers.  ...  As video enhancement tasks execute on resource-limited mobile devices and potentially in real time, there is a need for high-speed and high-quality video enhancement.  ... 
arXiv:2103.08764v2 fatcat:hquiqo4yevfnfoepqzi5q3jzka

MobileFusion: Real-Time Volumetric Surface Reconstruction and Dense Tracking on Mobile Phones

Peter Ondruska, Pushmeet Kohli, Shahram Izadi
2015 IEEE Transactions on Visualization and Computer Graphics  
Example objects scanned in real-time on a mobile phone using our system. Note we only use the internal RGB camera, and all computation is performed on the device.  ...  For each frame, the implicit surface is extracted for live user feedback and pose estimation.  ...  This trade-off led us to a simple but fast, block matching approach for disparity estimation.  ... 
doi:10.1109/tvcg.2015.2459902 pmid:26439826 fatcat:otd6j7ijebgqdi5apw44ec3jt4

Lightweight Monocular Depth with a Novel Neural Architecture Search Method [article]

Lam Huynh, Phong Nguyen, Jiri Matas, Esa Rahtu, Janne Heikkila
2021 arXiv   pre-print
This paper presents a novel neural architecture search method, called LiDNAS, for generating lightweight monocular depth estimation models.  ...  The LiDNAS method outperforms the state-of-the-art NAS approach, proposed for disparity and depth estimation, in terms of search efficiency and output model performance.  ...  This model can be deployed for depth estimation on hardware-limited devices.  ... 
arXiv:2108.11105v1 fatcat:arwrwe6mrfeffh6nlmmm6ig5ze

Light Field Depth Estimation on Off-the-Shelf Mobile GPU

Andre Ivan, Williem ., In Kyu Park
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
The experimental result shows that the light field depth estimation on mobile GPU obtains comparable performance as on the desktop CPU.  ...  To show the potential capability of light field processing on mobile GPU, we parallelize and optimize the state-of-the-art light field depth estimation which is essential to many light field applications  ...  Acknowledgment This work was supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korean government (MSIT) (2017-0-00142).  ... 
doi:10.1109/cvprw.2018.00106 dblp:conf/cvpr/IvanWP18 fatcat:c4hhqo7irzdpnfjw2wrsolfnge

Semi-dense visual odometry for AR on a smartphone

Thomas Schops, Jakob Engel, Daniel Cremers
2014 2014 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)  
We show how a simple world model for AR applications can be derived from semi-dense depth maps, and demonstrate the practical applicability in the context of an AR application in which simulated objects  ...  Depth is estimated by filtering over many small-baseline, pixel-wise stereo comparisons.  ...  Today, there are several keypoint based monocular VO and SLAM methods which run in real-time on mobile devices [14, 12] .  ... 
doi:10.1109/ismar.2014.6948420 dblp:conf/ismar/SchopsEC14 fatcat:55wtg7fpvvfzrm76djxoy53lvq

Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report [article]

Andrey Ignatov, Grigory Malivenko, David Plowman, Samarth Shukla, Radu Timofte, Ziyu Zhang, Yicheng Wang, Zilong Huang, Guozhong Luo, Gang Yu, Bin Fu, Yiran Wang (+26 others)
2021 arXiv   pre-print
Depth estimation is an important computer vision problem with many practical applications to mobile devices.  ...  While many solutions have been proposed for this task, they are usually very computationally expensive and thus are not applicable for on-device inference.  ...  Simple Baseline for Fast and Accurate Depth Estimation on Mobile Devices [74] Members: Ziyu Zhang (parkzyzhang@tencent.com), Yicheng Wang, Zilong Huang, Guozhong Luo, Gang Yu, Bin Fu Affiliations: Tencent  ... 
arXiv:2105.08630v1 fatcat:kfxoerr7ijh3to5wzzrkezore4

Making DensePose fast and light [article]

Ruslan Rakhimov, Emil Bogomolov, Alexandr Notchenko, Fung Mao, Alexey Artemov, Denis Zorin, Evgeny Burnaev
2020 arXiv   pre-print
To make things worse, mobile and embedded devices do not always have a powerful GPU inside.  ...  To enable Dense Pose inference on the end device with current models, one needs to support an expensive server-side infrastructure and have a stable internet connection.  ...  The authors acknowledge the usage of the Skoltech CDISE HPC cluster Zhores for obtaining the results presented in this paper.  ... 
arXiv:2006.15190v3 fatcat:epwsa6psobbyxmnh24b4blly4q

Dense reconstruction on-the-fly

A. Wendel, M. Maurer, G. Graber, T. Pock, H. Bischof
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
The distributed reconstruction pipeline is based on state-of-the-art approaches to visual SLAM and variational depth map fusion, and is designed to exploit the individual capabilities of the system components  ...  We demonstrate the performance of our approach by capturing several indoor and outdoor scenes on-the-fly and by evaluating our results with respect to a ground-truth model.  ...  We thank NVIDIA for providing a Tegra3 prototype tablet and Ascending Technologies for providing thermal imagery.  ... 
doi:10.1109/cvpr.2012.6247833 dblp:conf/cvpr/WendelMGPB12 fatcat:gwjfod7mtbga7luicrlucw6qla

Rapid scene reconstruction on mobile phones from panoramic images

Qi Pan, Clemens Arth, Gerhard Reitmayr, Edward Rosten, Tom Drummond
2011 2011 10th IEEE International Symposium on Mixed and Augmented Reality  
By using a very fast and flexible algorithm a set of panoramic images is captured to form the basis of wide field-of-view images required for reliable and robust reconstruction.  ...  In this paper we present a novel system that allows for the generation of a coarse 3D model of the environment within several seconds on mobile smartphones.  ...  ACKNOWLEDGEMENTS This work was partially funded through the Christian Doppler Laboratory for Handheld Augmented Reality and the project HY-DROSYS (EU FP7/DGINFSO grant 224416).  ... 
doi:10.1109/ismar.2011.6092370 dblp:conf/ismar/PanARRD11 fatcat:254fajflg5fz3oikstx23jdi5m

Rapid scene reconstruction on mobile phones from panoramic images

Qi Pan, Clemens Arth, Gerhard Reitmayr, Edward Rosten, Tom Drummond
2011 2011 10th IEEE International Symposium on Mixed and Augmented Reality  
By using a very fast and flexible algorithm a set of panoramic images is captured to form the basis of wide field-of-view images required for reliable and robust reconstruction.  ...  In this paper we present a novel system that allows for the generation of a coarse 3D model of the environment within several seconds on mobile smartphones.  ...  ACKNOWLEDGEMENTS This work was partially funded through the Christian Doppler Laboratory for Handheld Augmented Reality and the project HY-DROSYS (EU FP7/DGINFSO grant 224416).  ... 
doi:10.1109/ismar.2011.6162872 fatcat:5dkilggrzjc73plsocbdgsh6qi

Fast Neural Architecture Search for Lightweight Dense Prediction Networks [article]

Lam Huynh, Esa Rahtu, Jiri Matas, Janne Heikkila
2022 arXiv   pre-print
LDP is fast and suitable for various dense estimation problems, unlike previous NAS methods that are either computational demanding or deployed only for a single subtask.  ...  The performance of LPD is evaluated on monocular depth estimation, semantic segmentation, and image super-resolution tasks on diverse datasets, including NYU-Depth-v2, KITTI, Cityscapes, COCO-stuff, DIV2K  ...  The proposed framework takes in a dataset as input to search for the best possible model. This model can be deployed for depth estimation on hardware-limited devices.  ... 
arXiv:2203.01994v3 fatcat:nnz34pody5banfrqpkaanpszau

Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution [article]

Yushu Wu, Yifan Gong, Pu Zhao, Yanyu Li, Zheng Zhan, Wei Niu, Hao Tang, Minghai Qin, Bin Ren, Yanzhi Wang
2022 arXiv   pre-print
Instead of measuring the speed on mobile devices at each iteration during the search process, a speed model incorporated with compiler optimizations is leveraged to predict the inference latency of the  ...  However, prior methods typically suffer from large amounts of computations and huge power consumption, causing difficulties for real-time inference, especially on resource-limited platforms such as mobile  ...  We can adopt NAS or pruning methods to find a lightweight SR model with fast speed on mobile devices.  ... 
arXiv:2207.12577v1 fatcat:66iokedkubbxflr7b4yunnbqja

Fast Metric Acquisition with Mobile Devices [article]

Valeria Garro, Giovanni Pintore, Fabio Ganovelli, Enrico Gobbetti, Roberto Scopigno
2016 Vision  
We present a novel algorithm for fast metric reconstruction on mobile devices using a combination of image and inertial acceleration data.  ...  In contrast to previous approaches to this problem, our algorithm does not require a long acquisition time or intensive data processing and can be implemented entirely on common IMU-enabled tablet and  ...  Acknowledgements This work has received funding from the European Union's Seventh Framework Programme for research, technological development and demonstration under grant agreement no 607737 (VASCO).  ... 
doi:10.2312/vmv.20161339 dblp:conf/vmv/GarroPGGS16 fatcat:k3mxt3ns2nb4doxpyuk3pvcl5e
« Previous Showing results 1 — 15 out of 18,095 results