TY - GEN
T1 - Reflection Scene Separation From a Single Image
AU - Wan, Renjie
AU - Shi, Boxin
AU - Li, Haoliang
AU - Duan, Ling Yu
AU - Kot, Alex C.
N1 - This research is supported by the National Research Foundation, Prime Minister’s Office, Singapore, under the NRFNSFC grant NRF2016NRF-NSFC001-098 and NTU-PKU Joint Research Institute with donation from Ng Teng Fong Charitable Foundation. The research work was done at the Rapid-Rich Object Search (ROSE) Lab, Nanyang Technological University, Singapore. This research is in part supported by the National Natural Science Foundation of China under Grants U1611461 and 61872012, National Key R&D Program of China (2019YFF0302902), Shenzhen Municipal Science and Technology Program under Grant JCYJ20170818141146428, and Beijing Academy of Artificial Intelligence (BAAI).
Publisher Copyright:
© 2020 IEEE
PY - 2020/6/13
Y1 - 2020/6/13
N2 - For images taken through glass, existing methods focus on the restoration of the background scene by regarding the reflection components as noise. However, the scene reflected by glass surface also contains important information to be recovered, especially for the surveillance or criminal investigations. In this paper, instead of removing reflection components from the mixture image, we aim at recovering reflection scenes from the mixture image. We first propose a strategy to obtain such ground truth and its corresponding input images. Then, we propose a two-stage framework to obtain the visible reflection scene from the mixture image. Specifically, we train the network with a shift-invariant loss which is robust to misalignment between the input and output images. The experimental results show that our proposed method achieves promising results.
AB - For images taken through glass, existing methods focus on the restoration of the background scene by regarding the reflection components as noise. However, the scene reflected by glass surface also contains important information to be recovered, especially for the surveillance or criminal investigations. In this paper, instead of removing reflection components from the mixture image, we aim at recovering reflection scenes from the mixture image. We first propose a strategy to obtain such ground truth and its corresponding input images. Then, we propose a two-stage framework to obtain the visible reflection scene from the mixture image. Specifically, we train the network with a shift-invariant loss which is robust to misalignment between the input and output images. The experimental results show that our proposed method achieves promising results.
UR - http://www.scopus.com/inward/record.url?scp=85094863642&partnerID=8YFLogxK
U2 - 10.1109/CVPR42600.2020.00247
DO - 10.1109/CVPR42600.2020.00247
M3 - Conference proceeding
AN - SCOPUS:85094863642
SN - 9781728171692
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 2395
EP - 2403
BT - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PB - IEEE
T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020
Y2 - 14 June 2020 through 19 June 2020
ER -
