CN112767253B - 一种多尺度特征融合的双目图像超分辨率重建方法 - Google Patents
一种多尺度特征融合的双目图像超分辨率重建方法 Download PDFInfo
- Publication number
- CN112767253B CN112767253B CN202110158551.0A CN202110158551A CN112767253B CN 112767253 B CN112767253 B CN 112767253B CN 202110158551 A CN202110158551 A CN 202110158551A CN 112767253 B CN112767253 B CN 112767253B
- Authority
- CN
- China
- Prior art keywords
- image
- feature
- resolution
- feature tensor
- residual
- 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.)
- Active
Links
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
- G06T3/4076—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 using the original low-resolution images to iteratively correct the high-resolution images
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (3)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110158551.0A CN112767253B (zh) | 2021-02-05 | 2021-02-05 | 一种多尺度特征融合的双目图像超分辨率重建方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110158551.0A CN112767253B (zh) | 2021-02-05 | 2021-02-05 | 一种多尺度特征融合的双目图像超分辨率重建方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112767253A CN112767253A (zh) | 2021-05-07 |
CN112767253B true CN112767253B (zh) | 2022-05-24 |
Family
ID=75705081
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110158551.0A Active CN112767253B (zh) | 2021-02-05 | 2021-02-05 | 一种多尺度特征融合的双目图像超分辨率重建方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112767253B (zh) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113344791B (zh) * | 2021-07-05 | 2022-06-10 | 中山大学 | 基于空洞卷积和特征融合的双目超分辨率图像检测方法、系统及介质 |
CN113887568B (zh) * | 2021-09-09 | 2024-02-06 | 西安理工大学 | 一种各向异性卷积的双目图像立体匹配方法 |
CN113822805B (zh) * | 2021-10-13 | 2022-10-18 | 深圳市优像科技有限公司 | 图像超分辨率重建方法、中药植物叶病诊断方法及设备 |
CN114170078B (zh) * | 2021-11-18 | 2025-05-02 | 天讯瑞达通信技术有限公司 | 基于图神经网络的双目图像超分辨率方法及装置 |
CN114881858B (zh) * | 2022-05-17 | 2024-12-27 | 东南大学 | 基于多注意力机制融合的轻量级双目图像超分辨率方法 |
CN114926343A (zh) * | 2022-06-08 | 2022-08-19 | 南京大学 | 一种基于金字塔融合注意力网络的图像超分辨率方法 |
CN116033155A (zh) * | 2022-09-28 | 2023-04-28 | 北京大学深圳研究生院 | 双目图像的压缩方法、设备及可读存储介质 |
CN115358931B (zh) * | 2022-10-20 | 2023-01-03 | 运易通科技有限公司 | 一种用于仓库物流系统的图像重建方法及设备 |
CN115880157B (zh) * | 2023-01-06 | 2023-05-26 | 中国海洋大学 | 一种k空间金字塔特征融合的立体图像超分辨率重建方法 |
CN116309072A (zh) * | 2023-03-29 | 2023-06-23 | 西南科技大学 | 一种特征通道分离与融合的双目图像超分辨率方法 |
CN118736053B (zh) * | 2024-09-04 | 2024-11-05 | 浙江长龙海运有限公司 | 一种基于可视化神经网络的多比例尺热力图构建方法 |
CN119228651B (zh) * | 2024-10-16 | 2025-03-21 | 中国矿业大学 | 一种基于高频特征增强的图像超分辨率重建方法及装置 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110070489A (zh) * | 2019-04-30 | 2019-07-30 | 中国人民解放军国防科技大学 | 一种基于视差注意力机制的双目图像超分辨方法 |
CN110390696A (zh) * | 2019-07-03 | 2019-10-29 | 浙江大学 | 一种基于图像超分辨率重建的圆孔位姿视觉检测方法 |
CN111626927A (zh) * | 2020-04-09 | 2020-09-04 | 上海交通大学 | 采用视差约束的双目图像超分辨率方法、系统及装置 |
-
2021
- 2021-02-05 CN CN202110158551.0A patent/CN112767253B/zh active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110070489A (zh) * | 2019-04-30 | 2019-07-30 | 中国人民解放军国防科技大学 | 一种基于视差注意力机制的双目图像超分辨方法 |
CN110390696A (zh) * | 2019-07-03 | 2019-10-29 | 浙江大学 | 一种基于图像超分辨率重建的圆孔位姿视觉检测方法 |
CN111626927A (zh) * | 2020-04-09 | 2020-09-04 | 上海交通大学 | 采用视差约束的双目图像超分辨率方法、系统及装置 |
Non-Patent Citations (2)
Title |
---|
SP-Flow:Self-supervised optical flow correspondence point prediction for real-time SLAM;Zixuan Qin 等;《Computer Aided Geometric Design》;20200831;第82卷;第1-13页 * |
基于泰勒展开式与曲率逆向驱动的图像超分辨算法;赵小乐 等;《计算机应用》;20141210;第34卷(第12期);第3570-3575页 * |
Also Published As
Publication number | Publication date |
---|---|
CN112767253A (zh) | 2021-05-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112767253B (zh) | 一种多尺度特征融合的双目图像超分辨率重建方法 | |
Meng et al. | High-dimensional dense residual convolutional neural network for light field reconstruction | |
CN111311490B (zh) | 基于多帧融合光流的视频超分辨率重建方法 | |
CN109741260B (zh) | 一种基于深度反投影网络的高效超分辨率方法 | |
CN112507997B (zh) | 一种基于多尺度卷积和感受野特征融合的人脸超分辨系统 | |
Wu et al. | Revisiting light field rendering with deep anti-aliasing neural network | |
Li et al. | Dlgsanet: lightweight dynamic local and global self-attention networks for image super-resolution | |
CN113139898B (zh) | 基于频域分析和深度学习的光场图像超分辨率重建方法 | |
CN110197468A (zh) | 一种基于多尺度残差学习网络的单图像超分辨重建算法 | |
CN111028150A (zh) | 一种快速时空残差注意力视频超分辨率重建方法 | |
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 | |
CN114820323B (zh) | 一种基于立体注意力机制的多尺度残差双目图像超分辨率方法 | |
CN117952830B (zh) | 一种基于迭代交互指导的立体图像超分辨率重建方法 | |
CN117745541A (zh) | 一种基于轻量级混合注意力网络的图像超分辨率重建方法 | |
CN114359041A (zh) | 一种光场图像空间超分辨率重建方法 | |
CN117474764B (zh) | 一种针对复杂退化模型下遥感图像的高分辨率重建方法 | |
CN115546505A (zh) | 一种基于深度学习的无监督单目图像深度估计方法 | |
CN112767246B (zh) | 光场图像多倍率空间超分辨方法及装置 | |
CN114418850A (zh) | 一种融合图卷积的有参考图像超分辨率重构方法 | |
Chai et al. | Super-resolution reconstruction for stereoscopic omnidirectional display systems via dynamic convolutions and cross-view transformer | |
Chandramouli et al. | A generative model for generic light field reconstruction | |
CN116309067B (zh) | 一种光场图像空间超分辨率方法 | |
CN114881858B (zh) | 基于多注意力机制融合的轻量级双目图像超分辨率方法 | |
CN118864562B (zh) | 基于逐级长程捕捉与细节恢复的轻量双目立体匹配方法 | |
CN116309072A (zh) | 一种特征通道分离与融合的双目图像超分辨率方法 |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20240612 Address after: Floor 14 and 15, Building 1, Block 2, East Tianfu Haichuangyuan, Zizhou Avenue Road, Chengdu City, Sichuan Province, 610000 Patentee after: Southwest University of Science and Technology Sichuan Tianfu New Area Innovation Research Institute Country or region after: China Address before: 621010, No. 59, Qinglong Avenue, Fucheng District, Sichuan, Mianyang Patentee before: Southwest University of Science and Technology Country or region before: China |
|
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20240906 Address after: 11th Floor, Building 1, No. 118 Jitai Fifth Road, High tech Zone, Chengdu, Sichuan, 610000 Patentee after: CHENGDU HORSENT WISELINK TECHNOLOGY Co.,Ltd. Country or region after: China Address before: Floor 14 and 15, Building 1, Block 2, East Tianfu Haichuangyuan, Zizhou Avenue Road, Chengdu City, Sichuan Province, 610000 Patentee before: Southwest University of Science and Technology Sichuan Tianfu New Area Innovation Research Institute Country or region before: China |
|
TR01 | Transfer of patent right |