Light-Field Dataset for Disparity Based Depth Estimation In this paper, we have introduced a real and synthetic light-field dataset for disparity-based light-field depth estimation We also provided stereo light-field data for real scenes using a Lytro Illum camera with a mechanical gantry system, and synthetic stereo scenes were rendered using Blender
Inria synthetic light field datasets The datasets were generated in order to test depth estimation method in light field They were submitted along with our proposed depth estimation framework in TIP, July 2019
3DLF-Scan dataset: Multi-sensor 3D light-field and structured-light . . . We assembled this dataset to (i) stress-test high-fidelity sparse-to-dense depth completion on light-field imagery, (ii) provide pose-aware, 360° turntable sequences for multi-view and SfM MVS algorithms, and (iii) supply calibration artifacts for reproducible pipelines in common 3D toolchains
A New Parallel Intelligence Based Light Field Dataset for Depth . . . - MDPI In this paper, we firstly propose a new static light field dataset that contains up to 50 scenes and takes 8 to 10 perspectives for each scene, with the ground truth including disparities, depths, surface normals, segmentations, and object poses
Light-Field - University of California, San Diego By combining the real light field captured using Lytro Illum and synthetic light field rendering of 3D scenes from UnrealCV, we provide a large-scale blurry light field dataset to train the network
A New Parallel Intelligence Based Light Field Dataset for Depth . . . In this paper, we firstly propose a new static light field dataset that contains up to 50 scenes and takes 8 to 10 perspectives for each scene, with the ground truth including disparities, depths, surface normals, segmentations, and object poses
Fast and Efficient Depth Map Estimation from Light Field te depth map estimation from a lenslet light field camera In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1547– 1555, 2015 1