Benchmarking Single-Image Reflection Removal Algorithms

Renjie Wan1, Boxin Shi2, Ling-Yu Duan3, Ah-Hwee Tan1, and Alex C. Kot1

1Nanyang Technological University 2National Institute of Advanced Industrial Science and Technology 3Peking University

the framework picture

We propose the `SIR2' benchmark dataset with a large number and a great diversity of mixture images, and ground truth of background and reflection. Our dataset includes the controlled scenes taken indoor and wild scenes taken outdoor.

One part of the controlled scene is composed by a set of solid objects, which uses commonly available daily-life objects (e.g. ceramix mugs, plush toys, fruits, etc.) for both the background and the reflected scenes. The other parts of the controlled scenes use five different postcards and combines them in a pair-wise manner by using each card as background and reflection, respectively.

The wild scenes are with real-world objects of complex reflectance (car, tree leaves, glass windows, etc), various distances and scales (residential halls, gardens, and lecture room, etc), and different illuminations (direct sunlight, cloudy sky light and twilight, etc.).

  • Nov 23, 2017: Since this work is supported by Rapid-Rice Object Search Lab, if you need the data, please send emails to me.
  • July 21, 2017: The webpage is online now. The dataset will come soon!
  • Dataset
    The dataset can be found here.

    Please email us at wanpeoplejie [at] for any inquiries.