News

• [NOTE] I accidentally deleted the pre-trained model for MSD dataset. The current pre-trained model for MSD is re-trained and may produce slightly different results compared with those reported the original paper.
• We provide a new splited PMD dataset, which is spited into 5,096 training images and 571 testing images for convenient evaluation. Some ambiguous samples from the previous version of PMD dataset are filtered.

Updated results in PMD splited

Abstract

The mirror detection problem is important as mirrors can affect the performances of many vision tasks. It is a difficult problem as it requires an understanding of global scene semantics. Recently, a method was proposed to detect mirrors by learning multi-level contextual contrasts between inside and outside of mirrors, which helps locate mirror edges implicitly. We observe that the content of a mirror reflects the content of its surrounding, separated by the edge of the mirror. Hence, we propose a model in this paper to progressively learn the content similarity between the inside and outside of the mirror while explicitly detecting the mirror edges. Our work has two main contributions. First, we propose a new relational contextual contrasted local (RCCL) module to extract and compare the mirror features with its corresponding context features, and an edge detection and fusion (EDF) module to learn the features of mirror edges in complex scenes via explicit supervision. Second, we construct a challenging benchmark dataset of 6,461 mirror images. Unlike the existing MSD dataset, which has limited diversity, our dataset covers a variety of scenes and is much larger in scale. Experimental results show that our model outperforms relevant state-of-the-art methods.

Dataset Preview

Introduction Video

Citation

 @inproceedings{PMD:2020,
    title={Progressive Mirror Detection},
    author={Lin, Jiaying and Wang, Guodong and Lau, Rynson W.H.},
    booktitle={Proc. CVPR},
    year={2020}
} 

Contact

jiayinlin5-c at my.cityu.edu.hk