Documents
Poster
DEPTH ESTIMATION NETWORK FOR DUAL DEFOCUSED IMAGES WITH DIFFERENT DEPTH-OF-FIELD
![](https://sigport.org/sites/default/files/styles/home/public/ICIP_2018_2_0.jpg?itok=3Zvo4ksZ)
- Citation Author(s):
- Submitted by:
- gwangmo song
- Last updated:
- 5 October 2018 - 2:44am
- Document Type:
- Poster
- Document Year:
- 2018
- Event:
- Presenters:
- Gwangmo Song
- Paper Code:
- 2863
- Categories:
- Log in to post comments
In this work, we propose an algorithm to estimate the depth map of a scene using defocused images. In particular, the depth map is estimated using two defocused images with different depth-of-field for the same scene. Similar to the approach of the general depth from defocus (DFD), the proposed algorithm obtains the depth information from the
blurredness of the object. Moreover, our proposed algorithm dramatically improves the accuracy by using both the shallow and deep depth-of-field images, simultaneously. Especially, we propose a novel depth estimation network for dual defocused images using convolutional neural network (CNN). We evaluate our proposed network on the NYU-v2 dataset and show superior performance compared to the existing techniques.