CN106296749B - 基于l1范数约束的rgb-d图像本征分解方法 - Google Patents
基于l1范数约束的rgb-d图像本征分解方法 Download PDFInfo
- Publication number
- CN106296749B CN106296749B CN201610645510.3A CN201610645510A CN106296749B CN 106296749 B CN106296749 B CN 106296749B CN 201610645510 A CN201610645510 A CN 201610645510A CN 106296749 B CN106296749 B CN 106296749B
- Authority
- CN
- China
- Prior art keywords
- pixel
- matrix
- value
- point
- indicate
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
-
- 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
- G06T2207/10024—Color image
Abstract
Description
图像1 | 图像2 | 图像3 | 图像4 | 图像5 | 平均值 | |
DSSIM(反照率) | 0.2808 | 0.1905 | 0.3785 | 0.2793 | 0.3302 | 0.2799 |
DSSIM(亮度) | 0.2687 | 0.1822 | 0.2628 | 0.2787 | 0.2609 | 0.2609 |
LMSE(反照率) | 0.0152 | 0.0137 | 0.0211 | 0.0080 | 0.0165 | 0.0149 |
LMSE(亮度) | 0.0287 | 0.0116 | 0.0115 | 0.0170 | 0.0400 | 0.0214 |
Claims (3)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610645510.3A CN106296749B (zh) | 2016-08-05 | 2016-08-05 | 基于l1范数约束的rgb-d图像本征分解方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610645510.3A CN106296749B (zh) | 2016-08-05 | 2016-08-05 | 基于l1范数约束的rgb-d图像本征分解方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106296749A CN106296749A (zh) | 2017-01-04 |
CN106296749B true CN106296749B (zh) | 2019-10-18 |
Family
ID=57666970
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610645510.3A Active CN106296749B (zh) | 2016-08-05 | 2016-08-05 | 基于l1范数约束的rgb-d图像本征分解方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106296749B (zh) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108765448B (zh) * | 2018-05-28 | 2022-01-07 | 青岛大学 | 一种基于改进tv-l1模型的虾苗计数分析方法 |
CN109903320B (zh) * | 2019-01-28 | 2021-06-08 | 浙江大学 | 一种基于肤色先验的人脸本征图像分解方法 |
CN110929686A (zh) * | 2019-12-09 | 2020-03-27 | 佛山市熠瞳科技有限公司 | 本征图像分解方法、装置、设备及可读存储介质 |
CN112053338A (zh) * | 2020-08-31 | 2020-12-08 | 浙江商汤科技开发有限公司 | 图像分解方法和相关装置、设备 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104268897A (zh) * | 2014-10-28 | 2015-01-07 | 天津大学 | 一种协同本征图像分解方法 |
CN104484884A (zh) * | 2014-12-30 | 2015-04-01 | 天津大学 | 一种基于多尺度l0稀疏约束的本征图像分解方法 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9299188B2 (en) * | 2013-08-08 | 2016-03-29 | Adobe Systems Incorporated | Automatic geometry and lighting inference for realistic image editing |
-
2016
- 2016-08-05 CN CN201610645510.3A patent/CN106296749B/zh active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104268897A (zh) * | 2014-10-28 | 2015-01-07 | 天津大学 | 一种协同本征图像分解方法 |
CN104484884A (zh) * | 2014-12-30 | 2015-04-01 | 天津大学 | 一种基于多尺度l0稀疏约束的本征图像分解方法 |
Non-Patent Citations (3)
Title |
---|
A Simple Model for Intrinsic Image Decomposition with Depth Cues;Qifeng Chen 等;《2013 IEEE International Conference on Computer Vision》;20131208;241-248 * |
Intrinsic Scene Decomposition from RGB-D images;Mohammed Hachama 等;《2015 IEEE International Conference on Computer Vision》;20151213;810-818 * |
本征图像分解方法与应用研究;戴海鹏;《万方数据》;20151203;1-43 * |
Also Published As
Publication number | Publication date |
---|---|
CN106296749A (zh) | 2017-01-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110008915B (zh) | 基于掩码-rcnn进行稠密人体姿态估计的系统及方法 | |
CN108875935B (zh) | 基于生成对抗网络的自然图像目标材质视觉特征映射方法 | |
CN110781895B (zh) | 一种基于卷积神经网络的图像语义分割方法 | |
CN106296749B (zh) | 基于l1范数约束的rgb-d图像本征分解方法 | |
CN103093444B (zh) | 基于自相似性和结构信息约束的图像超分辨重建方法 | |
CN102881011B (zh) | 基于区域分割的肖像光照迁移方法 | |
CN109712203A (zh) | 一种基于自注意力生成对抗网络的图像着色方法 | |
CN103914699A (zh) | 一种基于色彩空间的自动唇彩的图像增强的方法 | |
CN108090403A (zh) | 一种基于3d卷积神经网络的人脸动态识别方法及系统 | |
CN105551010A (zh) | 基于nsct及深度信息激励pcnn的多聚焦图像融合方法 | |
CN109242834A (zh) | 一种基于卷积神经网络的无参考立体图像质量评价方法 | |
CN103617596A (zh) | 一种基于流型转换的图像色彩风格变换方法 | |
CN104899921A (zh) | 基于多模态自编码模型的单视角视频人体姿态恢复方法 | |
CN110097617B (zh) | 基于卷积神经网络与显著性权重的图像融合方法 | |
CN111046868B (zh) | 基于矩阵低秩稀疏分解的目标显著性检测方法 | |
Premaratne et al. | Image matching using moment invariants | |
CN103065282A (zh) | 一种基于稀疏线性系统的图像融合方法 | |
Severino et al. | A new approach for color image segmentation based on color mixture | |
CN101359366B (zh) | 一种图形匹配识别系统及其实现方法 | |
Huang et al. | A fully-automatic image colorization scheme using improved CycleGAN with skip connections | |
CN110148083B (zh) | 基于快速bemd和深度学习的图像融合方法 | |
CN104143203A (zh) | 一种图像编辑传播方法 | |
CN104240197A (zh) | 一种保持对比度、颜色一致性和灰度像素特征的消色算法 | |
CN102289661A (zh) | 一种基于谱匹配的三维网格模型的匹配方法 | |
CN104463917B (zh) | 基于除法归一化的图像视觉显著性检测方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into 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: 20200715 Address after: 411, block a, Zhizao street, Zhongguancun, No. 45, Chengfu Road, Haidian District, Beijing 100080 Patentee after: Beijing Youke Nuclear Power Technology Development Co.,Ltd. Address before: 300072 Tianjin City, Nankai District Wei Jin Road No. 92 Patentee before: Tianjin University |
|
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20201014 Address after: 115, 1 / F, block C, Zhizao street, Zhongguancun, 45 Chengfu Road, Haidian District, Beijing Patentee after: Beijing chaofang Information Technology Co.,Ltd. Address before: 411, block a, Zhizao street, Zhongguancun, No. 45, Chengfu Road, Haidian District, Beijing 100080 Patentee before: Beijing Youke Nuclear Power Technology Development Co.,Ltd. |
|
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20210208 Address after: 518005 1001, building C2, Nanshan wisdom garden, 1001 Xueyuan Avenue, Changyuan community, Taoyuan Street, Nanshan District, Shenzhen City, Guangdong Province Patentee after: Shenzhen Lingyun Shixun Technology Co.,Ltd. Address before: 115, 1 / F, block C, Zhizao street, Zhongguancun, 45 Chengfu Road, Haidian District, Beijing Patentee before: Beijing chaofang Information Technology Co.,Ltd. |
|
TR01 | Transfer of patent right |