Cited 0 time in
Cited 17 time in
Depth completion with deep geometry and context guidance
- Depth completion with deep geometry and context guidance
- Lee, Byeong-Uk; Jeon, Hae-Gon; Im, Sunghoon; Kweon, In So
- DGIST Authors
- Im, Sunghoon
- Issue Date
- 2019 International Conference on Robotics and Automation, ICRA 2019, 3281-3287
- In this paper, we present an end-to-end convolutional neural network (CNN) for depth completion. Our network consists of a geometry network and a context network. The geometry network, a single encoder-decoder network, learns to optimize a multi-task loss to generate an initial propagated depth map and a surface normal. The complementary outputs allow it to correctly propagate initial sparse depth points in slanted surfaces. The context network extracts a local and a global feature of an image to compute a bilateral weight, which enables it to preserve edges and fine details in the depth maps. At the end, a final output is produced by multiplying the initially propagated depth map with the bilateral weight. In order to validate the effectiveness and the robustness of our network, we performed extensive ablation studies and compared the results against state-of-the-art CNN-based depth completions, where we showed promising results on various scenes.
- Institute of Electrical and Electronics Engineers Inc.
- Related Researcher
Computer Vision Lab.
Computer Vision; Deep Learning; Robot Vision
There are no files associated with this item.
- Department of Electrical Engineering and Computer ScienceComputer Vision Lab.2. Conference Papers
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.