Release Agreement for SIR2 Dataset

SIR2 Benchmark Dataset consist of 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.).

The SIR2 Benchmark Dataset is the property of the Rapid-Rich Object Search (ROSE) Lab at the Nanyang Technological University, Singapore.

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.

Terms and Conditions:

The use of this dataset is governed by the following terms and conditions:

Related Publications

All publications using the SIR2 Benchmark dataset should include the following acknowledgement: "(Portions of) the research in this paper used the 'SIR2' Benchmark 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, "Benchamrking Single-image Reflection Removal Algorithms", in International Conferenceon Computer Vision (ICCV), 2017 [PDF] [bibtex].


By completing this online form, you have accepted the above terms & conditions and agree to include the above acknowledgements in your publications.

We need to validate all requests. Therefore we require you to provide full name of organisation and affiliated email address.

Project Title
Requester's Details
Title
First Name Last Name
Designation example: post-graduate student, research associate, research fellow, faculty, system analyst, data scientist
Email Address
Organisation
Country
Supervisor's Details (Leave all fields below blank if Supervisor is same as Requester)
Title
First Name Last Name
Email Address
Designation example: research fellow, faculty, lead data scientist, chief data officer