The SIR2 Benchmark Dataset
We propose the Single Image Reflection Removal(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.).
Size of the data:
The overall size of the data is 186 MB
To ease the downloading, we separate the modalities of the samples into different files.
The size of each modality is shown in the below table:
|Postcard Dataset||200 image triplets (600 images), 173,538 KB|
|Solid Object Dataset||200 image triplets (600 images), 13,520 KB|
|Wild Scene Dataset||100 image triplets (300 images), 4,154 KB|
|Total:||500 image triplets (1500 images), 186 MB|
How to obtain the dataset:
Researchers can register an account, submite the request form and accept the Release Aggrement. We will validate your request and grand approve for downloading the datasets.
More information related with our dataset, and the latest published results on our dataset can be found here.
Usage for Academic Reseach
The image database is released for academic research only, and is free to researchers from educational or research institutes for non-commercial purposes.
All publications using the `SIR2' dataset should include the following acknowledgement: “(Portions of) the research in this paper used the `SIR2' Dataset made available by the ROSE Lab at the Nanyang Technological University, Singapore.”
Furthermore, these publications should cite the following reference:
Renjie Wan, Boxin Shi, Ling-Yu Duan, Ah-Hwee Tan, and Alex C. Kot, "Benchmarking Single-image Reflection Removal Algorithms", in International Conference on Computer Vision (ICCV), 2017 [PDF].