Object pre-localization from computer-generated holograms is still an open problem in the current state of the art. In this work, we propose the use of the hologram phase space representation to determine a set of regions of interest where the searched object can be located. The extracted regions can be used to pre-locate the object in 3D space and are further refined to produce a more accurate depth estimate. An iterative refinement method is proposed for 1D holograms and is extended in a parsimonious version for 2D holograms. A series of experiments are conducted to assess the quality of the extracted regions of interest and the sparse depth estimate produced by the iterative refinement method. Experimental results show that it is possible to pre-localize the object in 3D space from the phase space representation and thus to improve the calculation time by reducing the number of operations and numerical reconstructions necessary for the application of s (DFF) methods. Using the proposed methodology, the time for the application of the DFF method is reduced by half, and the accuracy is increased by a factor of three.
Recovering the scene depth map from a computer-generated hologram is a problem that remains unsolved, despite the growing interest in the subject. In this paper, we propose to study the application of depth-from-focus (DFF) methods to retrieve the depth information from the hologram. We discuss the different hyperparameters that are required for the application of the method and their impact on the final result. The obtained results show that DFF methods can be used for depth estimation from the hologram if the set of hyperparameters is well chosen.
Despite the growing interest for Holography, there is a lack of publicly available three-dimensional hologram sequences for the evaluation of video codecs with interframe compression mechanisms such as motion estimation and compensation. In this paper, we report the first large-scale dataset containing 18 holographic videos computed with three different resolutions and pixel pitches. By providing the color and depth images corresponding to each hologram frame, our dataset can be used in additional applications such as the validation of 3D scene geometry retrieval or deep learning-based hologram synthesis methods. Altogether, our dataset comprises 5400 pairs of RGB-D images and holograms, totaling more than 550 GB of data.
Information extraction from computer-generated holograms using learning-based methods is a topic that has not received much research attention. In this article, we propose and study two learning-based methods to extract the depth information from a hologram and compare their performance with that of classical depth from focus (DFF) methods. We discuss the main characteristics of a hologram and how these characteristics can affect model training. The obtained results show that it is possible to extract depth information from a hologram if the problem formulation is well-posed. The proposed methods are faster and more accurate than state-of-the-art DFF methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.