Deep Specialized Network for Illuminant Estimation
Refereed conference paper presented and published in conference proceedings


引用次數
替代計量分析
.

其它資訊
摘要

Illuminant estimation to achieve color constancy is an ill-posed problem. Searching the large hypothesis space for an accurate illuminant estimation is hard due to the ambiguities of unknown reflections and local patch appearances. In this work, we propose a novel Deep Specialized Network (DS-Net) that is adaptive to diverse local regions for estimating robust local illuminants. This is achieved through a new convolutional network architecture with two interacting sub-networks, i.e. an hypotheses network (HypNet) and a selection network (SelNet). In particular, HypNet generates multiple illuminant hypotheses that inherently capture different modes of illuminants with its unique two-branch structure. SelNet then adaptively picks for confident estimations from these plausible hypotheses. Extensive experiments on the two largest color constancy benchmark datasets show that the proposed 'hypothesis selection' approach is effective to overcome erroneous estimation. Through the synergy of HypNet and SelNet, our approach outperforms state-of-the-art methods such as [1-3].

出版社接受日期29.07.2016
著者SHI Wu, LOY Chen Change, TANG Xiaoou
會議名稱The 14th European Conference on Computer Vision
會議開始日08.10.2016
會議完結日16.10.2016
會議地點Amsterdam
會議國家/地區荷蘭
會議論文集題名Computer Vision – ECCV 2016. Lecture Notes in Computer Science
出版年份2016
月份10
卷號9908
出版社Springer
國際標準書號978-3-319-46492-3
國際標準期刊號0302-9743
語言美式英語

上次更新時間 2020-06-08 於 03:02