Globally consistent depth labeling of 4D light fields

By Sven Wanner, Bastian Goldlücke. 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

395 citations recorded by the source corpus.

How researchers see this paper

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

Learning-based view synthesis for light field cameras (2016, positive): “Since our disparity estimation CNN is trained to directly minimize the synthesis error, our estimated disparities are more suitable for this application than existing disparity estimation techniques [Wanner and Goldluecke 2012; Tao et al. 2013; Wang et al. 2015; Jeon et al. 2015] (see Fig.”
Depth from Combining Defocus and Correspondence Using Light-Field Cameras (2013, background): “[11, 33] propose using global label consistency and slope analysis to estimate depth.”
Occlusion-Aware Depth Estimation Using Light-Field Cameras (2015, methodology): “11), demonstrating higher-quality depth recovery than previous work [8, 20, 22, 26].”
Robust depth estimation for light field via spinning parallelogram operator (2016, neutral): “On the other hand, because of the continuous angular pace, some methods based on estimating the slopes of the lines in he Epipolar Plane Image (EPI) [13,14] have been developed.”
Light Field Image Processing: An Overview (2017, neutral): “To address the problem, Wanner and Goldluecke [66], [112] presented a con-”