CN112150531B - 一种鲁棒的自监督学习单帧图像深度估计方法 - Google Patents
一种鲁棒的自监督学习单帧图像深度估计方法 Download PDFInfo
- Publication number
- CN112150531B CN112150531B CN202011057349.0A CN202011057349A CN112150531B CN 112150531 B CN112150531 B CN 112150531B CN 202011057349 A CN202011057349 A CN 202011057349A CN 112150531 B CN112150531 B CN 112150531B
- Authority
- CN
- China
- Prior art keywords
- depth
- image
- loss
- frame
- pixel
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 239000011159 matrix material Substances 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 16
- 230000015556 catabolic process Effects 0.000 claims description 3
- 238000006731 degradation reaction Methods 0.000 claims description 3
- 238000013441 quality evaluation Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 2
- 101150040772 CALY gene Proteins 0.000 claims 1
- 230000000873 masking effect Effects 0.000 claims 1
- 230000000007 visual effect Effects 0.000 claims 1
- 238000005286 illumination Methods 0.000 abstract description 20
- 230000006870 function Effects 0.000 abstract description 11
- 238000004364 calculation method Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 7
- 230000002411 adverse Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000008030 elimination Effects 0.000 description 3
- 238000003379 elimination reaction Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 101100456045 Schizosaccharomyces pombe (strain 972 / ATCC 24843) map3 gene Proteins 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000009508 confectionery Nutrition 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/207—Analysis of motion for motion estimation over a hierarchy of resolutions
-
- 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
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (8)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011057349.0A CN112150531B (zh) | 2020-09-29 | 2020-09-29 | 一种鲁棒的自监督学习单帧图像深度估计方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011057349.0A CN112150531B (zh) | 2020-09-29 | 2020-09-29 | 一种鲁棒的自监督学习单帧图像深度估计方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112150531A CN112150531A (zh) | 2020-12-29 |
CN112150531B true CN112150531B (zh) | 2022-12-09 |
Family
ID=73894627
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011057349.0A Active CN112150531B (zh) | 2020-09-29 | 2020-09-29 | 一种鲁棒的自监督学习单帧图像深度估计方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112150531B (zh) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113139990B (zh) * | 2021-05-08 | 2022-03-15 | 电子科技大学 | 一种基于内容感知的深度网格流鲁棒图像对齐方法 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110335337A (zh) * | 2019-04-28 | 2019-10-15 | 厦门大学 | 一种基于端到端半监督生成对抗网络的视觉里程计的方法 |
CN110503680A (zh) * | 2019-08-29 | 2019-11-26 | 大连海事大学 | 一种基于非监督的卷积神经网络单目场景深度估计方法 |
CN110910437A (zh) * | 2019-11-07 | 2020-03-24 | 大连理工大学 | 一种复杂室内场景的深度预测方法 |
CN111325797A (zh) * | 2020-03-03 | 2020-06-23 | 华东理工大学 | 一种基于自监督学习的位姿估计方法 |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018119807A1 (zh) * | 2016-12-29 | 2018-07-05 | 浙江工商大学 | 一种基于卷积神经网络的时空一致性深度图序列的生成方法 |
US10803546B2 (en) * | 2017-11-03 | 2020-10-13 | Baidu Usa Llc | Systems and methods for unsupervised learning of geometry from images using depth-normal consistency |
CN108765479A (zh) * | 2018-04-04 | 2018-11-06 | 上海工程技术大学 | 利用深度学习对视频序列中单目视图深度估计优化方法 |
CN108961327B (zh) * | 2018-05-22 | 2021-03-30 | 深圳市商汤科技有限公司 | 一种单目深度估计方法及其装置、设备和存储介质 |
US10957062B2 (en) * | 2018-10-31 | 2021-03-23 | Bentley Systems, Incorporated | Structure depth-aware weighting in bundle adjustment |
CN110009674B (zh) * | 2019-04-01 | 2021-04-13 | 厦门大学 | 基于无监督深度学习的单目图像景深实时计算方法 |
CN110443842B (zh) * | 2019-07-24 | 2022-02-15 | 大连理工大学 | 基于视角融合的深度图预测方法 |
CN110910447B (zh) * | 2019-10-31 | 2023-06-06 | 北京工业大学 | 一种基于动静态场景分离的视觉里程计方法 |
CN111369608A (zh) * | 2020-05-29 | 2020-07-03 | 南京晓庄学院 | 一种基于图像深度估计的视觉里程计方法 |
-
2020
- 2020-09-29 CN CN202011057349.0A patent/CN112150531B/zh active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110335337A (zh) * | 2019-04-28 | 2019-10-15 | 厦门大学 | 一种基于端到端半监督生成对抗网络的视觉里程计的方法 |
CN110503680A (zh) * | 2019-08-29 | 2019-11-26 | 大连海事大学 | 一种基于非监督的卷积神经网络单目场景深度估计方法 |
CN110910437A (zh) * | 2019-11-07 | 2020-03-24 | 大连理工大学 | 一种复杂室内场景的深度预测方法 |
CN111325797A (zh) * | 2020-03-03 | 2020-06-23 | 华东理工大学 | 一种基于自监督学习的位姿估计方法 |
Also Published As
Publication number | Publication date |
---|---|
CN112150531A (zh) | 2020-12-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111062872B (zh) | 一种基于边缘检测的图像超分辨率重建方法及系统 | |
CN111489372B (zh) | 基于级联卷积神经网络的视频前背景分离方法 | |
CN110782490A (zh) | 一种具有时空一致性的视频深度图估计方法及装置 | |
CN111105382B (zh) | 视频修复方法 | |
CN112580473B (zh) | 一种融合运动特征的视频超分辨率重构方法 | |
CN113284061B (zh) | 一种基于梯度网络的水下图像增强方法 | |
CN111612703A (zh) | 一种基于生成对抗网络的图像盲去模糊方法 | |
CN112270691B (zh) | 一种基于动态滤波器网络的单目视频结构和运动预测方法 | |
CN112150531B (zh) | 一种鲁棒的自监督学习单帧图像深度估计方法 | |
CN114170286A (zh) | 一种基于无监督深度学习的单目深度估计方法 | |
CN112164010A (zh) | 一种多尺度融合卷积神经网络图像去雾方法 | |
CN114494050A (zh) | 一种基于事件相机的自监督视频去模糊和图像插帧方法 | |
CN111429375A (zh) | 日间图像参照辅助的夜晚监控视频质量提升方法 | |
Mathai et al. | Automatic 2D to 3D video and image conversion based on global depth map | |
RU2754965C1 (ru) | Устройство восстановления изображений в пространстве кватернионов с использованием анизотропного градиента и нейронной сети | |
CN112532999B (zh) | 基于深度神经网络的数字视频删帧篡改检测方法 | |
Lin et al. | NightRain: Nighttime Video Deraining via Adaptive-Rain-Removal and Adaptive-Correction | |
CN112767261A (zh) | 一种基于广义非凸张量鲁棒主成分分析模型的针对彩色图像和视频的非局部去噪框架 | |
Zhang et al. | Single image haze removal for aqueous vapour regions based on optimal correction of dark channel | |
Wu et al. | MSDB-based CNN architecture for image dehazing in driverless cars | |
Wang et al. | A novel framework for object removal from digital photograph | |
CN112164009B (zh) | 基于两层全连接条件随机场模型的深度图结构修复方法 | |
CN113724168B (zh) | 一种飞机图像去雾方法及系统 | |
Yang et al. | Hardware-Oriented Shallow Joint Demosaicing and Denoising | |
CN116092069A (zh) | 一种基于轮廓建模的自然场景视频文本检测方法及系统 |
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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Sun Jinqiu Inventor after: Zhang Yanning Inventor after: Li Rui Inventor after: Zhu Yu Inventor after: He Xiantuo Inventor after: Li Xianjun Inventor after: Li Junzhi Inventor before: Sun Jinqiu Inventor before: Zhang Yanning Inventor before: Li Rui Inventor before: Zhu Yu Inventor before: He Xiantuo Inventor before: Li Xianjun |