Nianyi Li, Jinwei Ye, Yu Ji, Haibin Ling, Jingyi Yu. Saliency Detection on Light Field. CVPR 2014. [PDF]
We acquire 100 light fields using the Lytro light field camera. For each light field, we provide: (a) Raw light field data, (b) A rough focal stack (c) An all-focus image deriving from focal stack (d) The ground truth corresponding to all-focus image.
To get a valid ground-truth, we ask three individuals to manually segment the saliency regions from the all-focus image. The result are deemed ground truth only when all three results are consistent (i.e., they have an overlap of over 90%)
For each example below, we show results by our model and the ground-truth.
LFSD (100 images)
- LFSD raw image data (1.28GB)
- LFSD focus stack (77.5MB)
- LFSD all focus images (2.34MB)
- LFSD ground-truth masks (0.35MB)
- LFSD depth-map (0.54MB)
Code & Result