Weakly Supervised Deep Depth Prediction Leveraging Ground Control Points for Guidance
Despite the tremendous progress made in learning-based depth prediction, most methods rely heavily on large amounts of dense ground-truth depth data for training. To solve the tradeoff between the labeling cost and precision, we propose a novel weakly supervised approach, namely, the Guided-Net, by...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8570753/ |
| _version_ | 1818644967443136512 |
|---|---|
| author | Liang Du Jiamao Li Xiaoqing Ye Xiaolin Zhang |
| author_facet | Liang Du Jiamao Li Xiaoqing Ye Xiaolin Zhang |
| author_sort | Liang Du |
| collection | DOAJ |
| description | Despite the tremendous progress made in learning-based depth prediction, most methods rely heavily on large amounts of dense ground-truth depth data for training. To solve the tradeoff between the labeling cost and precision, we propose a novel weakly supervised approach, namely, the Guided-Net, by incorporating robust ground control points for guidance. By exploiting the guidance from ground control points, disparity edge gradients, and image appearance constraints, our improved network with deformable convolutional layers is empowered to learn in a more efficient way. The experiments on the KITTI, Cityscapes, and Make3D datasets demonstrate that the proposed method yields a performance superior to that of the existing weakly supervised approaches and achieves results comparable to those of the semisupervised and supervised frameworks. |
| first_indexed | 2024-12-17T00:23:16Z |
| format | Article |
| id | doaj.art-e612785974a143b6b6ff5915587d1774 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T00:23:16Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e612785974a143b6b6ff5915587d17742022-12-21T22:10:31ZengIEEEIEEE Access2169-35362019-01-0175736574810.1109/ACCESS.2018.28857738570753Weakly Supervised Deep Depth Prediction Leveraging Ground Control Points for GuidanceLiang Du0https://orcid.org/0000-0002-7952-5736Jiamao Li1Xiaoqing Ye2https://orcid.org/0000-0003-3268-880XXiaolin Zhang3Bio-Vision System Laboratory, State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, ChinaBio-Vision System Laboratory, State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, ChinaBio-Vision System Laboratory, State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, ChinaBio-Vision System Laboratory, State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, ChinaDespite the tremendous progress made in learning-based depth prediction, most methods rely heavily on large amounts of dense ground-truth depth data for training. To solve the tradeoff between the labeling cost and precision, we propose a novel weakly supervised approach, namely, the Guided-Net, by incorporating robust ground control points for guidance. By exploiting the guidance from ground control points, disparity edge gradients, and image appearance constraints, our improved network with deformable convolutional layers is empowered to learn in a more efficient way. The experiments on the KITTI, Cityscapes, and Make3D datasets demonstrate that the proposed method yields a performance superior to that of the existing weakly supervised approaches and achieves results comparable to those of the semisupervised and supervised frameworks.https://ieeexplore.ieee.org/document/8570753/Computer visionstereo image processingstereo visionweakly supervised learning |
| spellingShingle | Liang Du Jiamao Li Xiaoqing Ye Xiaolin Zhang Weakly Supervised Deep Depth Prediction Leveraging Ground Control Points for Guidance IEEE Access Computer vision stereo image processing stereo vision weakly supervised learning |
| title | Weakly Supervised Deep Depth Prediction Leveraging Ground Control Points for Guidance |
| title_full | Weakly Supervised Deep Depth Prediction Leveraging Ground Control Points for Guidance |
| title_fullStr | Weakly Supervised Deep Depth Prediction Leveraging Ground Control Points for Guidance |
| title_full_unstemmed | Weakly Supervised Deep Depth Prediction Leveraging Ground Control Points for Guidance |
| title_short | Weakly Supervised Deep Depth Prediction Leveraging Ground Control Points for Guidance |
| title_sort | weakly supervised deep depth prediction leveraging ground control points for guidance |
| topic | Computer vision stereo image processing stereo vision weakly supervised learning |
| url | https://ieeexplore.ieee.org/document/8570753/ |
| work_keys_str_mv | AT liangdu weaklysuperviseddeepdepthpredictionleveraginggroundcontrolpointsforguidance AT jiamaoli weaklysuperviseddeepdepthpredictionleveraginggroundcontrolpointsforguidance AT xiaoqingye weaklysuperviseddeepdepthpredictionleveraginggroundcontrolpointsforguidance AT xiaolinzhang weaklysuperviseddeepdepthpredictionleveraginggroundcontrolpointsforguidance |