Datasets and Benchmarks for Densely Sampled 4D Light Fields

By Sven Wanner, S. Meister, Bastian Goldlücke. International Symposium on Vision, Modeling, and Visualization, 2013

477 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 a Deep Convolutional Network for Light-Field Image Super-Resolution (2015, methodology): “To compare our method with the state-of-the-art LFSR approaches [20, 29], we select “Buddha” and “Mona” in the HCI dataset [31] as test images because these two images have fine structures and large depth variations.”
Light Field Super-Resolution with Zero-Shot Learning (2021, background): “The target datasets include Stanford Lytro Archive (Stan) [28], EPFL [29], HCI old (HCI1) [42], and HCI new (HCI2) [11].”
Robust depth estimation for light field via spinning parallelogram operator (2016, unknown): “Then, the performance of the proposed method on synthetic light field images with available ground truth [33] is evaluated.”
Occlusion-Aware Depth Estimation Using Light-Field Cameras (2015, background): “[23] Some intensities in the insets are adjusted for better contrast.”
Light Field Image Processing: An Overview (2017, methodology): “The scene in this figure is monasRoom from the HCI database [74].”
Accurate depth map estimation from a lenslet light field camera (2015, methodology): “The benchmark dataset [27] used for validation was composed of a 9 × 9 angular resolution of sub-aperture images with 0 .”