ConvNet-based Depth Estimation, Reflection Separation and Deblurring of Plenoptic Images

Chandramouli, Paramanand; Noroozi, Mehdi; Favaro, Paolo (2016). ConvNet-based Depth Estimation, Reflection Separation and Deblurring of Plenoptic Images. In: Lai, SH.; Lepetit, V.; Nishino, K.; Sato, Y. (eds.) Asian Conference on Computer Vision. ACCV 2016. Taipei, Taiwan. 20.-24.11.2016. 10.1007/978-3-319-54187-7_9

[img] Text
ConvNetDepth2016.pdf - Submitted Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (1MB) | Request a copy

In this paper, we address the problem of reflection removal and deblurring from a single image captured by a plenoptic camera. We develop a two-stage approach to recover the scene depth and high resolution textures of the reflected and transmitted layers. For depth estimation in the presence of reflections, we train a classifier through convolutional neural networks. For recovering high resolution textures, we assume that the scene is composed of planar regions and perform the reconstruction of each layer by using an explicit form of the plenoptic camera point spread function. The proposed framework also recovers the sharp scene texture with different motion blurs applied to each layer. We demonstrate our method on challenging real and synthetic images.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

08 Faculty of Science > Institute of Computer Science (INF)
08 Faculty of Science > Institute of Computer Science (INF) > Computer Vision Group (CVG)

UniBE Contributor:

Chandramouli, Paramanand; Noroozi, Mehdi and Favaro, Paolo

Subjects:

000 Computer science, knowledge & systems
500 Science > 510 Mathematics

Series:

Lecture Notes in Computer Science

Language:

English

Submitter:

Xiaochen Wang

Date Deposited:

13 Jun 2017 08:40

Last Modified:

21 Sep 2017 11:28

Publisher DOI:

10.1007/978-3-319-54187-7_9

Related URLs:

BORIS DOI:

10.7892/boris.98316

URI:

https://boris.unibe.ch/id/eprint/98316

Actions (login required)

Edit item Edit item
Provide Feedback