Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/142303
Title: Region-aware reflection removal with unified content and gradient priors
Authors: Wan, Renjie
Shi, Boxin
Duan, Ling-Yu
Tan, Ah-Hwee
Gao, Wen
Kot, Alex Chichung
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2018
Source: Wan, R., Shi, B., Duan, L.-Y., Tan, A.-H., Gao, W., & Kot, A. C. (2018). Region-aware reflection removal with unified content and gradient priors. IEEE Transactions on Image Processing, 27(6), 2927-2941. doi:10.1109/TIP.2018.2808768
Journal: IEEE Transactions on Image Processing
Abstract: Removing the undesired reflections in images taken through the glass is of broad application to various image processing and computer vision tasks. Existing single image based solutions heavily rely on scene priors such as separable sparse gradients caused by different levels of blur, and they are fragile when such priors are not observed. In this paper, we notice that strong reflections usually dominant a limited region in the whole image, and propose a Region-aware Reflection Removal (R3) approach by automatically detecting and heterogeneously processing regions with and without reflections. We integrate content and gradient priors to jointly achieve missing contents restoration as well as background and reflection separation in a unified optimization framework. Extensive validation using 50 sets of real data shows that the proposed method outperforms state-of-the-art on both quantitative metrics and visual qualities.
URI: https://hdl.handle.net/10356/142303
ISSN: 1057-7149
DOI: 10.1109/TIP.2018.2808768
Schools: School of Computer Science and Engineering 
School of Electrical and Electronic Engineering 
Interdisciplinary Graduate School (IGS) 
Rights: © 2018 IEEE. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

SCOPUSTM   
Citations 10

42
Updated on Feb 20, 2024

Web of ScienceTM
Citations 10

30
Updated on Oct 26, 2023

Page view(s)

255
Updated on Feb 27, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.