2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Imaging Without Borders

2021 IEEE International Conference on Image Processing

19-22 September 2021 • Anchorage, Alaska, USA

Login Paper Search My Schedule Paper Index Help

My ICIP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper ID3D-3.6
Paper Title ATTENTION-BASED SELF-SUPERVISED LEARNING MONOCULAR DEPTH ESTIMATION WITH EDGE REFINEMENT
Authors Chenweinan Jiang, Haichun Liu, Key Laboratory of Navigation and Location Based Services, Shanghai Jiao Tong University, China; Lanzhen Li, Shanghai West Hongqiao Navigation Technology CO.,LTD., China; Changchun Pan, Key Laboratory of Navigation and Location Based Services, Shanghai Jiao Tong University, China
Session3D-3: Stereoscopic and multiview processing
LocationArea J
Session Time:Wednesday, 22 September, 14:30 - 16:00
Presentation Time:Wednesday, 22 September, 14:30 - 16:00
Presentation Poster
Topic Three-Dimensional Image and Video Processing: Stereoscopic and multiview processing and display
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Learning depth from a single image extracted from unlabeled videos has been attracting significant attention in the past few years. In this work, we propose a new depth estimation neural network with edge refinement to predict depth. First, we introduce a dual attention module into depth prediction module to integrate global information into local features and improve local features’ capability of representation. Second, to increase the details between objects in scenes, we propose a subnetwork to predict edges in four directions and combine the predicted depth and edges to increase the details by propagation operation. Besides, we integrate the gradients of the image into the photometric reprojection loss to handle the confusion caused by changing brightness. We conduct experiments on KITTI datasets and show that our network achieves the state-of-art result.