NUS3D-Saliency Dataset

Introduction

Most previous studies on visual saliency have only focused on static or dynamic 2D scenes. Since the human visual system has evolved predominantly in natural three dimensional environments, it is important to study whether and how depth information influences visual saliency. In this work, we first collect a large human eye fixation database compiled from a pool of 600 2D-vs-3D image pairs viewed by 80 subjects, where the depth information is directly provided by the Kinect camera and the eye tracking data are captured in both 2D and 3D free-viewing experiments. We then analyze the major discrepancies between 2D and 3D human fixation data of the same scenes, which are further abstracted and modeled as novel depth priors. Finally, we evaluate the performances of several state-of-the-art saliency detection models over 3D images, and propose solutions to enhance their performances by integrating the depth priors.

The paper can be found here.

Description

NUS3D-Saliency Dataset is an eye fixation dataset which is collected from a pool of 600 images and 80 participants in both 2D and 3D scenes. The dataset provides color stimuli, depth maps, smooth depth maps, 2D and 3D fixation maps. 

Downloads

2D Fixation (Download)

3D Fixation (Download)

Color stimuli (Download)

Depth images (Download)

Smooth depth images (Download)

Citation

Please cite the following paper if you want to use this dataset in your research:

Congyan Lang*, Tam V. Nguyen*, Harish Katti*, Karthik Yadati, Mohan S. Kankanhalli, Shuicheng Yan: Depth Matters: Influence of Depth Cues on Visual Saliency. ECCV (2) 2012: 101-115 (* indicates equal contribution)

Acknowledgement 

This work is partially supported by National Nature Science Foundation of China (90820013, 61033013, 61100142), Beijing Jiaotong University Science Foundation No. 2011JBM219; MOE project MOE2010-T2-1-087, Singapore; and the A*STAR PSF Grant No. 102-101-0029 on "Characterizing and Exploiting Human Visual Attention for Automated Image Understanding and Description".

Contact

tamnguyen@nus.edu.sg