CASIA OpenIR  > 多模态人工智能系统全国重点实验室  > 三维可视计算
Single-Image Specular Highlight Removal via Real-World Dataset Construction
Wu ZQ(吴仲琦)1,2; Zhuang CQ(庄传青)2; Shi J(石剑)1,2; Guo JW(郭建伟)1,2; Xiao J(肖俊)2; Zhang XP(张晓鹏)1,2; Yan DM(严冬明)1,2

Specular reflections pose great challenges on various
multimedia and computer vision tasks, e.g., image segmentation,
detection and matching. In this paper, we build a large-scale
Paired Specular-Diffuse (PSD) image dataset, where the images
are carefully captured by using real-world objects and the
ground-truth specular-free diffuse images are provided. To the
best of our knowledge, this is the first real-world benchmark
dataset for specular highlight removal task, which is useful for
evaluating and encouraging new deep learning-based approaches.
Given this dataset, we present a novel Generative Adversarial
Network (GAN) for specular highlight removal from a single
image by introducing the detection of specular reflection infor-
mation as a guidance. Our network also makes full use of the
attention mechanism and is able to directly model the mapping
relation between the diffuse area and the specular highlight area
without any explicit estimation of the illumination. Experimental
results demonstrate that the proposed network is more effective
to remove specular reflection components with the guidance of
specular highlight detection than recent state-of-the-art methods.

KeywordSpecular highlight removal, PSD-Dataset, Deep learning
Indexed BySCI
Document Type期刊论文
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Wu ZQ,Zhuang CQ,Shi J,et al. Single-Image Specular Highlight Removal via Real-World Dataset Construction[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2021:12.
APA Wu ZQ.,Zhuang CQ.,Shi J.,Guo JW.,Xiao J.,...&Yan DM.(2021).Single-Image Specular Highlight Removal via Real-World Dataset Construction.IEEE TRANSACTIONS ON MULTIMEDIA,12.
MLA Wu ZQ,et al."Single-Image Specular Highlight Removal via Real-World Dataset Construction".IEEE TRANSACTIONS ON MULTIMEDIA (2021):12.
Files in This Item: Download All
File Name/Size DocType Version Access License
2021_TMM_Single-Imag(49307KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
2021_TMM_Specular_Hi(20836KB)期刊论文作者接受稿开放获取CC BY-NC-SAView
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wu ZQ(吴仲琦)]'s Articles
[Zhuang CQ(庄传青)]'s Articles
[Shi J(石剑)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wu ZQ(吴仲琦)]'s Articles
[Zhuang CQ(庄传青)]'s Articles
[Shi J(石剑)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wu ZQ(吴仲琦)]'s Articles
[Zhuang CQ(庄传青)]'s Articles
[Shi J(石剑)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2021_TMM_Single-Image_Specular_Highlight_Removal_via_Real-World_Dataset_Construction.pdf
Format: Adobe PDF
File name: 2021_TMM_Specular_Highlight_Removal _supplement.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.