Depth Reconstruction from Single Images Using a Convolutional Neural Network and a Condition Random Field Model
This paper presents an effective approach for depth reconstruction from a single image through the incorporation of semantic information and local details from the image. A unified framework for depth acquisition is constructed by joining a deep Convolutional Neural Network (CNN) and a continuous pa...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/5/1318 |
| _version_ | 1798002474227859456 |
|---|---|
| author | Dan Liu Xuejun Liu Yiguang Wu |
| author_facet | Dan Liu Xuejun Liu Yiguang Wu |
| author_sort | Dan Liu |
| collection | DOAJ |
| description | This paper presents an effective approach for depth reconstruction from a single image through the incorporation of semantic information and local details from the image. A unified framework for depth acquisition is constructed by joining a deep Convolutional Neural Network (CNN) and a continuous pairwise Conditional Random Field (CRF) model. Semantic information and relative depth trends of local regions inside the image are integrated into the framework. A deep CNN network is firstly used to automatically learn a hierarchical feature representation of the image. To get more local details in the image, the relative depth trends of local regions are incorporated into the network. Combined with semantic information of the image, a continuous pairwise CRF is then established and is used as the loss function of the unified model. Experiments on real scenes demonstrate that the proposed approach is effective and that the approach obtains satisfactory results. |
| first_indexed | 2024-04-11T11:52:45Z |
| format | Article |
| id | doaj.art-220b7e671f9c426694d7aa1d654b22e8 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T11:52:45Z |
| publishDate | 2018-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-220b7e671f9c426694d7aa1d654b22e82022-12-22T04:25:15ZengMDPI AGSensors1424-82202018-04-01185131810.3390/s18051318s18051318Depth Reconstruction from Single Images Using a Convolutional Neural Network and a Condition Random Field ModelDan Liu0Xuejun Liu1Yiguang Wu2Faculty of Geomatics, East China University of Technology, Nanchang 330013, ChinaKey Laboratory of Virtual Geographic Environment, Nanjing Normal University, Nanjing 210023, ChinaKey Laboratory of Virtual Geographic Environment, Nanjing Normal University, Nanjing 210023, ChinaThis paper presents an effective approach for depth reconstruction from a single image through the incorporation of semantic information and local details from the image. A unified framework for depth acquisition is constructed by joining a deep Convolutional Neural Network (CNN) and a continuous pairwise Conditional Random Field (CRF) model. Semantic information and relative depth trends of local regions inside the image are integrated into the framework. A deep CNN network is firstly used to automatically learn a hierarchical feature representation of the image. To get more local details in the image, the relative depth trends of local regions are incorporated into the network. Combined with semantic information of the image, a continuous pairwise CRF is then established and is used as the loss function of the unified model. Experiments on real scenes demonstrate that the proposed approach is effective and that the approach obtains satisfactory results.http://www.mdpi.com/1424-8220/18/5/1318depth reconstructionsingle imageconvolutional neural networkconditional random field |
| spellingShingle | Dan Liu Xuejun Liu Yiguang Wu Depth Reconstruction from Single Images Using a Convolutional Neural Network and a Condition Random Field Model Sensors depth reconstruction single image convolutional neural network conditional random field |
| title | Depth Reconstruction from Single Images Using a Convolutional Neural Network and a Condition Random Field Model |
| title_full | Depth Reconstruction from Single Images Using a Convolutional Neural Network and a Condition Random Field Model |
| title_fullStr | Depth Reconstruction from Single Images Using a Convolutional Neural Network and a Condition Random Field Model |
| title_full_unstemmed | Depth Reconstruction from Single Images Using a Convolutional Neural Network and a Condition Random Field Model |
| title_short | Depth Reconstruction from Single Images Using a Convolutional Neural Network and a Condition Random Field Model |
| title_sort | depth reconstruction from single images using a convolutional neural network and a condition random field model |
| topic | depth reconstruction single image convolutional neural network conditional random field |
| url | http://www.mdpi.com/1424-8220/18/5/1318 |
| work_keys_str_mv | AT danliu depthreconstructionfromsingleimagesusingaconvolutionalneuralnetworkandaconditionrandomfieldmodel AT xuejunliu depthreconstructionfromsingleimagesusingaconvolutionalneuralnetworkandaconditionrandomfieldmodel AT yiguangwu depthreconstructionfromsingleimagesusingaconvolutionalneuralnetworkandaconditionrandomfieldmodel |