CN112070667A - 一种多尺度特征融合的视频超分辨率重建的方法 - Google Patents
一种多尺度特征融合的视频超分辨率重建的方法 Download PDFInfo
- Publication number
- CN112070667A CN112070667A CN202010818547.8A CN202010818547A CN112070667A CN 112070667 A CN112070667 A CN 112070667A CN 202010818547 A CN202010818547 A CN 202010818547A CN 112070667 A CN112070667 A CN 112070667A
- Authority
- CN
- China
- Prior art keywords
- patch
- size
- resolution
- super
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000004927 fusion Effects 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 34
- 230000003287 optical effect Effects 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims description 40
- 238000010586 diagram Methods 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 9
- 230000003321 amplification Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 238000002372 labelling Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 4
- 230000014759 maintenance of location Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4046—Scaling of whole images or parts thereof, e.g. expanding or contracting using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/269—Analysis of motion using gradient-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
Description
Claims (6)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010818547.8A CN112070667A (zh) | 2020-08-14 | 2020-08-14 | 一种多尺度特征融合的视频超分辨率重建的方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010818547.8A CN112070667A (zh) | 2020-08-14 | 2020-08-14 | 一种多尺度特征融合的视频超分辨率重建的方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112070667A true CN112070667A (zh) | 2020-12-11 |
Family
ID=73661751
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010818547.8A Pending CN112070667A (zh) | 2020-08-14 | 2020-08-14 | 一种多尺度特征融合的视频超分辨率重建的方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112070667A (zh) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115052187A (zh) * | 2022-04-26 | 2022-09-13 | 复旦大学 | 一种基于在线训练的超分辨率直播系统 |
WO2023179385A1 (zh) * | 2022-03-22 | 2023-09-28 | 中国科学院深圳先进技术研究院 | 一种视频超分方法、装置、设备及存储介质 |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090175552A1 (en) * | 2005-11-25 | 2009-07-09 | Stephane Mallat | Method and apparatus for enhancing signals with multiscale grouping bandelets |
CN107240066A (zh) * | 2017-04-28 | 2017-10-10 | 天津大学 | 基于浅层和深层卷积神经网络的图像超分辨率重建算法 |
US20180075581A1 (en) * | 2016-09-15 | 2018-03-15 | Twitter, Inc. | Super resolution using a generative adversarial network |
CN108537733A (zh) * | 2018-04-11 | 2018-09-14 | 南京邮电大学 | 基于多路径深度卷积神经网络的超分辨率重建方法 |
CN108537731A (zh) * | 2017-12-29 | 2018-09-14 | 西安电子科技大学 | 基于压缩多尺度特征融合网络的图像超分辨率重建方法 |
CN108550115A (zh) * | 2018-04-25 | 2018-09-18 | 中国矿业大学 | 一种图像超分辨率重建方法 |
CN108734660A (zh) * | 2018-05-25 | 2018-11-02 | 上海通途半导体科技有限公司 | 一种基于深度学习的图像超分辨率重建方法及装置 |
CN109118431A (zh) * | 2018-09-05 | 2019-01-01 | 武汉大学 | 一种基于多记忆及混合损失的视频超分辨率重建方法 |
CN109146788A (zh) * | 2018-08-16 | 2019-01-04 | 广州视源电子科技股份有限公司 | 基于深度学习的超分辨率图像重建方法和装置 |
CN109389556A (zh) * | 2018-09-21 | 2019-02-26 | 五邑大学 | 一种多尺度空洞卷积神经网络超分辨率重构方法及装置 |
WO2020047738A1 (zh) * | 2018-09-04 | 2020-03-12 | 安徽中科智能感知大数据产业技术研究院有限责任公司 | 多尺度特征融合网络结合定位模型的害虫自动计数方法 |
CN111127325A (zh) * | 2019-12-31 | 2020-05-08 | 珠海大横琴科技发展有限公司 | 基于循环神经网络的卫星视频超分辨率重建方法及系统 |
CN111311490A (zh) * | 2020-01-20 | 2020-06-19 | 陕西师范大学 | 基于多帧融合光流的视频超分辨率重建方法 |
-
2020
- 2020-08-14 CN CN202010818547.8A patent/CN112070667A/zh active Pending
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090175552A1 (en) * | 2005-11-25 | 2009-07-09 | Stephane Mallat | Method and apparatus for enhancing signals with multiscale grouping bandelets |
US20180075581A1 (en) * | 2016-09-15 | 2018-03-15 | Twitter, Inc. | Super resolution using a generative adversarial network |
CN107240066A (zh) * | 2017-04-28 | 2017-10-10 | 天津大学 | 基于浅层和深层卷积神经网络的图像超分辨率重建算法 |
CN108537731A (zh) * | 2017-12-29 | 2018-09-14 | 西安电子科技大学 | 基于压缩多尺度特征融合网络的图像超分辨率重建方法 |
CN108537733A (zh) * | 2018-04-11 | 2018-09-14 | 南京邮电大学 | 基于多路径深度卷积神经网络的超分辨率重建方法 |
CN108550115A (zh) * | 2018-04-25 | 2018-09-18 | 中国矿业大学 | 一种图像超分辨率重建方法 |
CN108734660A (zh) * | 2018-05-25 | 2018-11-02 | 上海通途半导体科技有限公司 | 一种基于深度学习的图像超分辨率重建方法及装置 |
CN109146788A (zh) * | 2018-08-16 | 2019-01-04 | 广州视源电子科技股份有限公司 | 基于深度学习的超分辨率图像重建方法和装置 |
WO2020047738A1 (zh) * | 2018-09-04 | 2020-03-12 | 安徽中科智能感知大数据产业技术研究院有限责任公司 | 多尺度特征融合网络结合定位模型的害虫自动计数方法 |
CN109118431A (zh) * | 2018-09-05 | 2019-01-01 | 武汉大学 | 一种基于多记忆及混合损失的视频超分辨率重建方法 |
CN109389556A (zh) * | 2018-09-21 | 2019-02-26 | 五邑大学 | 一种多尺度空洞卷积神经网络超分辨率重构方法及装置 |
WO2020056791A1 (zh) * | 2018-09-21 | 2020-03-26 | 五邑大学 | 一种多尺度空洞卷积神经网络超分辨率重构方法及装置 |
CN111127325A (zh) * | 2019-12-31 | 2020-05-08 | 珠海大横琴科技发展有限公司 | 基于循环神经网络的卫星视频超分辨率重建方法及系统 |
CN111311490A (zh) * | 2020-01-20 | 2020-06-19 | 陕西师范大学 | 基于多帧融合光流的视频超分辨率重建方法 |
Non-Patent Citations (5)
Title |
---|
卢涛;章瑾;陈白帆;管英杰;: "多尺度自适应配准的视频超分辨率算法", 武汉工程大学学报, no. 02, 15 April 2016 (2016-04-15) * |
戴光智;陈铁群;邱栋美;: "小波和插值结合应用于超声图像的超分辨率算法", 无损检测, no. 04, 10 April 2009 (2009-04-10) * |
李金航;肖亮;韦志辉;: "基于时空相关性的视频超分辨率重建算法", 计算机与数字工程, no. 04, 20 April 2020 (2020-04-20) * |
林琦;陈婧;曾焕强;朱建清;蔡灿辉;: "基于多尺度特征残差学习卷积神经网络的视频超分辨率方法", 信号处理, no. 01, 25 January 2020 (2020-01-25) * |
陈书贞;解小会;杨郁池;练秋生;: "利用多尺度卷积神经网络的图像超分辨率算法", 信号处理, no. 09, 25 September 2018 (2018-09-25) * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023179385A1 (zh) * | 2022-03-22 | 2023-09-28 | 中国科学院深圳先进技术研究院 | 一种视频超分方法、装置、设备及存储介质 |
CN115052187A (zh) * | 2022-04-26 | 2022-09-13 | 复旦大学 | 一种基于在线训练的超分辨率直播系统 |
CN115052187B (zh) * | 2022-04-26 | 2024-05-03 | 复旦大学 | 一种基于在线训练的超分辨率直播系统 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | Multi-memory convolutional neural network for video super-resolution | |
CN111311490B (zh) | 基于多帧融合光流的视频超分辨率重建方法 | |
Yi et al. | Multi-temporal ultra dense memory network for video super-resolution | |
CN108550115B (zh) | 一种图像超分辨率重建方法 | |
Sun et al. | Learning image compressed sensing with sub-pixel convolutional generative adversarial network | |
Li et al. | Learning a deep dual attention network for video super-resolution | |
CN112435191B (zh) | 一种基于多个神经网络结构融合的低照度图像增强方法 | |
CN112070667A (zh) | 一种多尺度特征融合的视频超分辨率重建的方法 | |
CN111696035A (zh) | 一种基于光流运动估计算法的多帧图像超分辨率重建方法 | |
CN115311720B (zh) | 一种基于Transformer的deepfake生成方法 | |
CN111640060A (zh) | 基于深度学习及多尺度残差稠密模块的单幅图像超分辨率重建方法 | |
Li et al. | Deep interleaved network for image super-resolution with asymmetric co-attention | |
CN112767283A (zh) | 一种基于多图像块划分的非均匀图像去雾方法 | |
Purohit et al. | Mixed-dense connection networks for image and video super-resolution | |
CN115953582B (zh) | 一种图像语义分割方法及系统 | |
Zhou et al. | Image super-resolution based on dense convolutional auto-encoder blocks | |
Chen et al. | MICU: Image super-resolution via multi-level information compensation and U-net | |
CN114881856A (zh) | 一种人体图像超分辨率重建方法、系统、装置及存储介质 | |
CN108924528B (zh) | 一种基于深度学习的双目风格化实时渲染方法 | |
Zhang et al. | Joint image demosaicking and denoising with mutual guidance of color channels | |
CN113052187A (zh) | 一种基于多尺度特征融合的全局特征对齐目标检测方法 | |
Zhou et al. | Deep fractal residual network for fast and accurate single image super resolution | |
Xu et al. | Learning lightweight Multi-Scale Feedback Residual network for single image super-resolution | |
CN109087247B (zh) | 一种对立体图像进行超分的方法 | |
CN115330631A (zh) | 一种基于堆叠沙漏网络的多尺度融合去雾方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20240516 Address after: 710000 No. B49, Xinda Zhongchuang space, 26th Street, block C, No. 2 Trading Plaza, South China City, international port district, Xi'an, Shaanxi Province Applicant after: Xi'an Huaqi Zhongxin Technology Development Co.,Ltd. Country or region after: China Address before: 710048 Shaanxi province Xi'an Beilin District Jinhua Road No. 5 Applicant before: XI'AN University OF TECHNOLOGY Country or region before: China |