BACK-PROJECTION PIPELINE

被引:2
|
作者
Michelini, Pablo Navarrete [1 ]
Liu, Hanwen [1 ]
Lu, Yunhua [1 ]
Jiang, Xingqun [1 ]
机构
[1] BOE Technol Co Ltd, Beijing, Peoples R China
来源
2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2021年
关键词
Super-resolution; back-projection; deep learning; multi-scale; causality; RENORMALIZATION-GROUP;
D O I
10.1109/ICIP42928.2021.9506014
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a simple extension of residual networks that works simultaneously in multiple resolutions for the problem of image super-resolution. Our network design is inspired by the iterative back-projection algorithm and seeks the more difficult task of learning how to enhance images. Compared to similar approaches, we propose a novel solution to make back-projections run in multiple resolutions by using a data pipeline workflow. Features are updated at multiple scales in each layer of the network. The update dynamic through these layers includes interactions between different resolutions in a way that is causal in scale, and it is represented by a system of ODEs, as opposed to a single ODE in the case of ResNets.
引用
收藏
页码:1949 / 1953
页数:5
相关论文
共 50 条
  • [31] REMOTE SENSING IMAGE SUPER-RESOLUTION VIA ENHANCED BACK-PROJECTION NETWORKS
    Dong, Xiaoyu
    Xi, Zhihong
    Sun, Xu
    Yang, Lina
    IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2020, : 1480 - 1483
  • [32] Image blind deblurring networks with back-projection feature fusion
    Li, Chi
    Kong, Weiwei
    Xue, Jiawei
    Wang, Ze
    Chang, Liang
    SIGNAL IMAGE AND VIDEO PROCESSING, 2023, 17 (05) : 2063 - 2071
  • [33] Arbitrary Back-Projection Networks for Image Super-Resolution
    Ma, Tingsong
    Tian, Wenhong
    INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE AND APPLICATIONS, 2020, 19 (04)
  • [34] Image blind deblurring networks with back-projection feature fusion
    Chi Li
    Weiwei Kong
    Jiawei Xue
    Ze Wang
    Liang Chang
    Signal, Image and Video Processing, 2023, 17 : 2063 - 2071
  • [35] Improved Back-Projection Cortical Potential Imaging by Multi-resolution Optimization Technique
    Haor, Dror
    Joffe, Roman
    Shavit, Reuven
    Peremen, Ziv
    Stern, Yaki
    Geva, Amir B.
    BRAIN TOPOGRAPHY, 2019, 32 (01) : 66 - 79
  • [36] An Iterative Back-Projection Technique for Single Image Super Resolution with Natural Texture Preservation
    Ngocho, Boniface M.
    Mwangi, Elijah
    EMERGING TRENDS IN ELECTRICAL, ELECTRONIC AND COMMUNICATIONS ENGINEERING, ELECOM 2016, 2017, 416 : 210 - 219
  • [37] SYNTHETIC APERTURE RADAR FOCUSING BASED ON BACK-PROJECTION AND COMPRESSIVE SENSING
    Focsa, Adrian
    Anghel, Andrei
    Toma, Stefan-Adrian
    Datcu, Mihai
    IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2020, : 2376 - 2379
  • [38] Fast Target Redetection for CAMSHIFT using Back-projection and Histogram Matching
    Basit, Abdul
    Dailey, Matthew N.
    Laksanacharoen, Pudit
    Moonrinta, Jednipat
    PROCEEDINGS OF THE 2014 9TH INTERNATIONAL CONFERENCE ON COMPUTER VISION, THEORY AND APPLICATIONS (VISAPP 2014), VOL 3, 2014, : 507 - 514
  • [39] Microcalcification detection on simple back-projection reconstructed slices using wavelets
    Bernard, S.
    Muller, S.
    Peters, G.
    Iordache, R.
    INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2006, 1 : 84 - 86
  • [40] Fixed-Point Processing of the SAR Back-Projection Algorithm on FPGA
    Hettiarachchi, Don Lahiru Nirmal
    Balster, Eric J.
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 : 10889 - 10902