Distilling Reflection Dynamics for Single-Image Reflection Removal

Quanlong Zheng      Xiaotian Qiao      Ying Cao      Shi Guo      Lei Zhang      Rynson Lau     

OPPO Research, City University of Hong Kong, The Hong Kong Polytechnic University, DAMO Academy, Alibaba Group


Single-image reflection removal (SIRR) aims to restore the transmitted image given a single image shot through glass or window. Existing methods rely mainly on information extracted from a single image along with some pre-defined priors, and fail to give satisfying results on real-world images, due to inherent ambiguity and lack of large and diverse real-world training data. In this paper, instead of reasoning about a single image only, we propose to distill a representation of reflection dynamics from multi-view images (i.e., the motions of reflection and transmission layers over time), and transfer the learned knowledge for the SIRR problem. In particular, we propose a teacher-student framework where the teacher network learns a representation of reflection dynamics by watching a sequence of multi-view images of a scene captured by a moving camera and teaches a student network to remove reflection from a single input image. In addition, we collect a large real-world multi-view reflection image dataset for reflection dynamics knowledge distillation. Extensive experiments show that our model yields state-of-the-art performances.


MKL Module


	author = {Zheng, Quanlong and Qiao, Xiaotian and Cao, Ying and Guo, Shi and Zhang, Lei and Lau, Rynson W.H.},
	title = {Distilling Reflection Dynamics for Single-Image Reflection Removal},
	booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
	month = {October},
	year = {2021},
	pages = {1886-1894}