Open access dataset of holographic videos for codec analysis and machine learning applications - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

Open access dataset of holographic videos for codec analysis and machine learning applications

Abstract

Despite the growing interest for Holography, there is a lack of publicly available three-dimensional hologram sequences for the evaluation of video codecs with inter-frame 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.
Fichier principal
Vignette du fichier
Open_access_dataset_of_holographic_videos_for_codec_analysis_and_machine_learning_applications.pdf (14.59 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04168692 , version 1 (21-07-2023)

Identifiers

Cite

Antonin Gilles, Patrick Gioia, Nabil Madali, Anas El Rhammad, Luce Morin. Open access dataset of holographic videos for codec analysis and machine learning applications. 2023 15th International Conference on Quality of Multimedia Experience (QoMEX), Jun 2023, Ghent, Belgium. pp.258-263, ⟨10.1109/QoMEX58391.2023.10178637⟩. ⟨hal-04168692⟩
31 View
14 Download

Altmetric

Share

Gmail Facebook X LinkedIn More