Filters








897 Hits in 6.1 sec

Front Matter: Volume 11049

Phooi Yee Lau, Kazuya Hayase, Qian Kemao, Wen-Nung Lie, Yung-Lyul Lee, Sanun Srisuk, Lu Yu
2019 International Workshop on Advanced Image Technology (IWAIT) 2019  
deep residual networks for image super-resolution 11049 09 3D scene reconstruction and object recognition for indoor scene SPECIAL SESSION II 0A A support system for archiving antique stereographs  ...  of lateral resolution in synthetic aperture super-resolution ultrasound imaging ix Proc. of SPIE Vol. 11049 1104901-9 Estimation of objective understanding measure based on student's nonverbal behavior  ... 
doi:10.1117/12.2530762 fatcat:lwxupqdakfhtdjxznvtohfj7di

Video Super Resolution Based on Deep Learning: A Comprehensive Survey [article]

Hongying Liu, Zhubo Ruan, Peng Zhao, Chao Dong, Fanhua Shang, Yuanyuan Liu, Linlin Yang, Radu Timofte
2022 arXiv   pre-print
In this survey, we comprehensively investigate 33 state-of-the-art video super-resolution (VSR) methods based on deep learning.  ...  It is well known that the leverage of information within video frames is important for video super-resolution.  ...  Yaowei Wang (Associate Professor with Peng Cheng Laboratory, Shenzhen, China) for their help in improving the quality of this manuscript.  ... 
arXiv:2007.12928v3 fatcat:nxoejcfdnzas3jznbqsale36ty

CNN-Based Macropixel-level Up-sampling for Plenoptic Image Coding

Kaiming Zhang, Xiaohuan Liu, Jing Zhang, Jingyi He, Yanan Shi, Zongqian Zhang
2019 IEEE Access  
With the insertion of a microlens array, plenoptic cameras can record both angular and spatial information of a scene on a plenoptic image.  ...  First, a macropixel-based down-sampling method, which performs the down-sampling in the units of macropixels, is developed for reducing the block resolution.  ...  Compared with conventional 2D technology, 3D technology requires richer stereo information of 3D scenes [3] , [4] .  ... 
doi:10.1109/access.2019.2922670 fatcat:edllnuje7rcmdo6q6qw675gjoy

Light Field Image Compression via CNN-Based EPI Super-Resolution and Decoder-Side Quality Enhancement

Jinbo Zhao, Ping An, Xinpeng Huang, Chao Yang, Liquan Shen
2019 IEEE Access  
Because of the capacity of capturing both the spatial and angular information of the light rays simultaneously, light field images (LFIs) contain richer scene information compared with conventional images  ...  The low-resolution EPIs generated from the sparse SAIs are super-resolved by a CNN and the outputs, high-resolution EPIs, are used to rebuild the dense SAIs.  ...  CNN-BASED SINGLE IMAGE SUPER-RESOLUTION A critical step in the proposed sparse coding framework is EPI super-resolution, so here is a brief introduction to the work of CNN-based single image super-resolution  ... 
doi:10.1109/access.2019.2930644 fatcat:xjj63zrdrncltbhtmbvwp6hd2a

cvpaper.challenge in 2015 - A review of CVPR2015 and DeepSurvey [article]

Hirokatsu Kataoka and Yudai Miyashita and Tomoaki Yamabe and Soma Shirakabe and Shin'ichi Sato and Hironori Hoshino and Ryo Kato and Kaori Abe and Takaaki Imanari and Naomichi Kobayashi and Shinichiro Morita and Akio Nakamura
2016 arXiv   pre-print
(TDU), and Univ. of Tsukuba that aims to systematically summarize papers on computer vision, pattern recognition, and related fields.  ...  The "cvpaper.challenge" is a group composed of members from AIST, Tokyo Denki Univ.  ...  In regard to the problem of super-resolution, a method using Self-Similarity based Super-Resolution was reported [563] .  ... 
arXiv:1605.08247v1 fatcat:cd4mc7uor5f2rpu3aketd6naf4

3D Appearance Super-Resolution With Deep Learning

Yawei Li, Vagia Tsiminaki, Radu Timofte, Marc Pollefeys, Luc Van Gool
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
On the other hand, the advent of deep learning-based methods has already a significant impact on the problem of video and image SR.  ...  We introduce a 3D appearance SR (3DASR) dataset based on the existing ETH3D [42] , SyB3R [31] , MiddleBury, and our Collection of 3D scenes from TUM [21] , Fountain [51] and Relief [53] .  ...  Figure 7 : 7 Figure 7: Network structure of (a) NLR and (b) NHR based on the the EDSR [36]. The change in the dimension of the blocks indicates the resolution change of the feature maps.  ... 
doi:10.1109/cvpr.2019.00990 dblp:conf/cvpr/LiTTPG19 fatcat:3im55qpcyvff3czj4ierq7tu7u

Survey of Deep-Learning Approaches for Remote Sensing Observation Enhancement

Grigorios Tsagkatakis, Anastasia Aidini, Konstantina Fotiadou, Michalis Giannopoulos, Anastasia Pentari, Panagiotis Tsakalides
2019 Sensors  
In this paper, we provide a comprehensive review of deep-learning methods for the enhancement of remote sensing observations, focusing on critical tasks including single and multi-band super-resolution  ...  Less yet equally important effort has also been allocated to addressing the challenges associated with the enhancement of low-quality observations from remote sensing platforms.  ...  In [91] , a CNN architecture based on the VDSR [31] is explored for super-resolution of video satellite frames.  ... 
doi:10.3390/s19183929 fatcat:fp7lezjwcfg5fol5hxmgoejg7a

Compressed-domain video classification with deep neural networks: "There's way too much information to decode the matrix"

Aaron Chadha, Alhabib Abbas, Yiannis Andreopoulos
2017 2017 IEEE International Conference on Image Processing (ICIP)  
changes in each video scene.  ...  We investigate video classification via a 3D deep convolutional neural network (CNN) that directly ingests compressed bitstream information.  ...  As exemplified in numerous works [16, 9] , the advantage of using a 3D CNN architecture with a 4D input, versus stacking the frames as channels and using a 3D input of size N × N × KT with a 2D CNN, is  ... 
doi:10.1109/icip.2017.8296598 dblp:conf/icip/ChadhaAA17 fatcat:jtsdez5crfbanj2dfotbfagtay

Efficient Geometry-aware 3D Generative Adversarial Networks [article]

Eric R. Chan, Connor Z. Lin, Matthew A. Chan, Koki Nagano, Boxiao Pan, Shalini De Mello, Orazio Gallo, Leonidas Guibas, Jonathan Tremblay, Sameh Khamis, Tero Karras, Gordon Wetzstein
2022 arXiv   pre-print
We demonstrate state-of-the-art 3D-aware synthesis with FFHQ and AFHQ Cats, among other experiments.  ...  In this work, we improve the computational efficiency and image quality of 3D GANs without overly relying on these approximations.  ...  We thank Alex Chan, Giap Nguyen, and Trevor Chan for help with figures and diagrams.  ... 
arXiv:2112.07945v2 fatcat:diysjwesgfbl7hlf2yn3s3lhb4

3D Appearance Super-Resolution with Deep Learning [article]

Yawei Li, Vagia Tsiminaki, Radu Timofte, Marc Pollefeys, Luc van Gool
2019 arXiv   pre-print
On the other hand, the advent of deep learning-based methods has already a significant impact on the problem of video and image SR.  ...  We introduce a 3D appearance SR (3DASR) dataset based on the existing ETH3D [42], SyB3R [31], MiddleBury, and our Collection of 3D scenes from TUM [21], Fountain [51] and Relief [53].  ...  Figure 7 : 7 Network structure of (a) NLR and (b) NHR based on the the EDSR [36] . The change in the dimension of the blocks indicates the resolution change of the feature maps.  ... 
arXiv:1906.00925v2 fatcat:5rpefoimmbfkrjdjwvy4kjpggu

Light Field Image Processing: An Overview

Gaochang Wu, Belen Masia, Adrian Jarabo, Yuchen Zhang, Liangyong Wang, Qionghai Dai, Tianyou Chai, Yebin Liu
2017 IEEE Journal on Selected Topics in Signal Processing  
We focus on all aspects of light field image processing, including basic light field representation and theory, acquisition, super-resolution, depth estimation, compression, editing, processing algorithms  ...  On the one hand, this higher-dimensional representation of visual data offers powerful capabilities for scene understanding, and substantially improves the performance of traditional computer vision problems  ...  Angular Super-resolution Many studies have focused on angular super-resolution using a small set of views with high spatial resolution.  ... 
doi:10.1109/jstsp.2017.2747126 fatcat:rvsfzvdxbbf4zesqdkaj3cseza

Video Classification With CNNs: Using The Codec As A Spatio-Temporal Activity Sensor [article]

Aaron Chadha, Alhabib Abbas, Yiannis Andreopoulos
2017 arXiv   pre-print
In order to evaluate the accuracy of a video classification framework based on such activity data, we independently train two CNN architectures on MB texture and MV correspondences and then fuse their  ...  Our approach begins with the observation that all modern video codecs divide the input frames into macroblocks (MBs).  ...  MV-based CNN approach have been presented in our corresponding conference paper [20] , MV-based selective MB texture decoding and the fusion of the temporal 3D-CNN with a spatial CNN are proposed here  ... 
arXiv:1710.05112v2 fatcat:yaxmhmffbjh4xfbjbsk2rtxdky

SASRT: Semantic-Aware Super-Resolution Transmission for Adaptive Video Streaming over Wireless Multimedia Sensor Networks

Jia Guo, Xiangyang Gong, Wendong Wang, Xirong Que, Jingyu Liu
2019 Sensors  
However, identifying semantic information on the user side may increase the computational cost of the user side. On the user side, video quality is enriched with super-resolution technologies.  ...  In this paper, a semantic-aware super-resolution transmission for adaptive video streaming system (SASRT) for WMSNs is presented.  ...  The algorithm improves the super-resolution video efficiency based on video characteristics such as timing.  ... 
doi:10.3390/s19143121 fatcat:yemwbxmiuvfoja57aszqjebahi

Review of light field technologies

Shuyao Zhou, Tianqian Zhu, Kanle Shi, Yazi Li, Wen Zheng, Junhai Yong
2021 Visual Computing for Industry, Biomedicine, and Art  
) scene reconstruction and view synthesis, and (5) industrial products because the technologies of lights fields also intersect with industrial applications.  ...  In this article, light field imaging is reviewed from the following aspects with an emphasis on the achievements of the past five years: (1) depth estimation, (2) content editing, (3) image quality, (4  ...  Acknowledgements The authors are grateful to Kuaishou Technology, University of California, Berkeley, and Tsinghua University.  ... 
doi:10.1186/s42492-021-00096-8 pmid:34862574 pmcid:PMC8642475 fatcat:6rq5rx5svrcerdr7rciaijy3k4

Multimodal Low Resolution Face and Frontal Gait Recognition from Surveillance Video

Sayan Maity, Mohamed Abdel-Mottaleb, Shihab S. Asfour
2021 Electronics  
Moreover, the classification accuracy on high-resolution face images is considerably higher.  ...  Biometric identification using surveillance video has attracted the attention of many researchers as it can be applicable not only for robust identification but also personalized activity monitoring.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/electronics10091013 doaj:46769ed6fbf842c8ac68ffb373934346 fatcat:bebdizpu3jcl3odzsw3zcgeaym
« Previous Showing results 1 — 15 out of 897 results