Saliency Detection on Light Field

By Nianyi Li, Jinwei Ye, Yu Ji, Haibin Ling, Jingyi Yu. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017

514 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/de1a6d76713aae081cff857033d38ac1d637e5af

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (2020, unknown): “Experiments are conducted on six public RGB-D benchmark datasets: NJU2K [34] (2000 samples), NLPR [44] (1000 samples), STERE [43] (1000 samples), RGBD135 [10] (135 samples), LFSD [35] (100 samples), and SIP [18] (929 samples).”
Light Field Image Processing: An Overview (2017, background): “[171] demonstrated that light fields can benefit saliency detection.”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, methodology): “We tested seven challenging RGB-D SOD datasets, i.e. , NJU2K [34], NLPR [49], STERE [47], SIP [20], DES [9], LFSD [41], and SSD [75].”
RGBD Salient Object Detection via Deep Fusion (2016, methodology): “Right: Quantitative comparisons on the LFSD dataset [54].”
Light field video capture using a learning-based hybrid imaging system (2017, unknown): “Finally, with the availability of light field videos, we would like to extend previous visual understanding work to videos, such as estimating saliency (Li et al. 2014), materials (Wang et al. 2016c), or matting (Cho et al. 2014) for dynamic objects and scenes.”
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders (2020, methodology): “Datasets: We perform experiments on six datasets including five widely used RGB-D saliency detection datasets (namely NJU2K [28], NLPR [41], SSB [40], LFSD [35], DES [8]) and one newly released dataset (SIP [18]).”
Learning a Deep Convolutional Network for Light-Field Image Super-Resolution (2015, background): “With richer angular information in a LF image, many studies have shown the potential to improve the performance of many computer vision applications such as alpha matting [6], saliency detection [17], LF panorama [3], and depth reconstruction [27, 33, 13].”
Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection (2019, unknown): “LFSD [27]: contains 100 images captured by Lytro camera.”
Visual Saliency Transformer (2021, methodology): “For RGB-D SOD, we use nine widely used benchmark datasets: STERE [46] (1,000 image pairs), LFSD [33] (100 image pairs), RGBD135 [9] (135 image pairs), SSD [90] (80 image pairs), NJUD [26] (1,985 image pairs), NLPR [51] (1,000 image pairs), DUTLF-Depth [52] (1,200 image pairs), SIP [15] (929 image pa”
Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection (2019, methodology): “Earlier work for SOD relies on various hand-designed feature [7, 26, 37, 41].”