Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A Spherical Light Field Database for Immersive Telecommunication and Telepresence Applications
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-). (Realistic3D)ORCID iD: 0000-0002-3210-8978
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-). (Realistic3D)ORCID iD: 0009-0006-9845-1652
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-). (Realistic3D)ORCID iD: 0009-0008-5477-0920
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-). (Realistic3D)ORCID iD: 0000-0001-7416-5615
Show others and affiliations
2024 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Immersive imaging technologies provide an enhanced user experience for visual applications and are getting ready for commonplace use by the industry and the general populace. In particular, light field is a promising technology that enables the capture and reproduction of real light rays from the scene, which can provide a backbone for immersive telecommunication and telepresence applications. Nevertheless, there are still many challenges in transmitting and reproducing light field data. This paper proposes a spherical light field dataset that can be used as a foundation for developing telepresence applications. The Spherical Light Field Database (SLFDB) consists of a light field of 60 views captured with an omnidirectional camera in 20 scenes. To show the usefulness of the proposed database, we provide two use cases: compression and viewpoint estimation. The initial results validate that the publicly available SLFDB will benefit the scientific community.

Place, publisher, year, edition, pages
IEEE, 2024.
Keywords [en]
light field, omnidirectional, compression, view synthesis, telepresence
National Category
Signal Processing Computer Engineering
Identifiers
URN: urn:nbn:se:miun:diva-52159DOI: 10.1109/QoMEX61742.2024.10598264ISI: 001289486600036Scopus ID: 2-s2.0-85201055576OAI: oai:DiVA.org:miun-52159DiVA, id: diva2:1890318
Conference
2024 16th International Conference on Quality of Multimedia Experience (QoMEX)
Projects
InfoVizPlenoptima
Funder
Knowledge Foundation, 2019-0251EU, Horizon 2020, 956770Available from: 2024-08-19 Created: 2024-08-19 Last updated: 2026-01-09
In thesis
1. VAE-Based Compression of Light Field Images Using Disentangled Latent Modeling and Perceptual Quality Assessment
Open this publication in new window or tab >>VAE-Based Compression of Light Field Images Using Disentangled Latent Modeling and Perceptual Quality Assessment
2026 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

The demand for immersive visual experiences in applications like virtual reality and telepresence has highlighted the limitations of traditional 2D imaging. Light field (LF) imaging addresses this by capturing a 4D representation of a scene, encoding both spatial (texture) and angular (viewpoint) information. This richness enables true parallax and depth perception but creates a significant data bottleneck, as the massive data volumes are a major obstacle to efficient storage, transmission, and real-time processing. Conventional compression methods often treat LF data as a simple sequence of images, failing to effectively exploit the underlying spatial-angular structure, which leads to sub-optimal performance.

This thesis addresses the challenge of efficient LF compression by developing a principled, learning-based framework centered on spatial-angular disentanglement. The core of the work is a series of Variational Autoencoder (VAE)-based architectures that explicitly separate spatial and angular features into distinct latent representations. This approach provides greater flexibility and efficiency by allowing each domain to be modeled according to its unique statistical properties. The foundational VAE model is progressively advanced through two key contributions: first, the integration of dual-hyperprior entropy models to learn tailored probability distributions for each latent stream, improving rate-distortion performance; and second, the introduction of an information-theoretic regularizer to ensure robust feature separation. Finally, a lightweight, modular compression pipeline is proposed to further compress these latent representations without requiring network retraining.

The proposed methods were rigorously evaluated on standard public LF datasets as well as a novel spherical LF dataset created as part of this research to support immersive telepresence scenarios. Objective evaluations demonstrate that the disentangled frameworks achieve a superior rate-distortion performance, with significant Bjontegaard Delta-Peak Signal-to-Noise Ratio (BD-PSNR) gains over state-of-the-art learning-based and traditional codecs. Crucially, the methods also offer substantially faster encoding and decoding times, a critical requirement for real-time applications. To assess perceptual performance, a formal subjective quality study was conducted, which confirmed that the proposed methods deliver improved visual quality, particularly in preserving angular consistency and reducing artifacts that impair the immersive experience.

In conclusion, this thesis demonstrates that explicitly disentangling, modeling, and compressing the spatial and angular components of light fields is a highly effective strategy. The developed frameworks and tools advance the state-of-the-art by providing practical and scalable solutions that balance compression efficiency, computational speed, and perceptual quality. This work makes a significant contribution toward the feasibility of using high-quality LF imaging in bandwidth-constrained immersive applications. This compilation thesis is based on the contributions of six peer-reviewed scientific publications.

Place, publisher, year, edition, pages
Sundsvall: Mid Sweden University, 2026. p. 70
Series
Mid Sweden University doctoral thesis, ISSN 1652-893X ; 440
Series
École Doctoral: Centre Inria de l’Université de Rennes ; 601
National Category
Computer Vision and Learning Systems
Identifiers
urn:nbn:se:miun:diva-56370 (URN)978-91-90017-39-5 (ISBN)
Public defence
2026-01-22, L111, Holmgatan 10, Sundsvall, 09:15 (English)
Opponent
Supervisors
Note

As part of a double degree with Université de Rennes.

Available from: 2026-01-09 Created: 2026-01-07 Last updated: 2026-02-12Bibliographically approved

Open Access in DiVA

SLFDB Author Accepted Manuscript(10482 kB)1175 downloads
File information
File name FULLTEXT02.pdfFile size 10482 kBChecksum SHA-512
c0f4be5e32a8e8dff69f897222b0eba1beae2571e9945d02d9c83c08377dbb68cf52da6eabc83f69de5db4b43a42a8a9fdfc64c2231c9e3cdaed66caeecc3b2f
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopusSLFDB preview page

Search in DiVA

By author/editor
Zerman, EminGond, ManuTakhtardeshir, SoheibOlsson, RogerSjöström, Mårten
By organisation
Department of Computer and Electrical Engineering (2023-)
Signal ProcessingComputer Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 1176 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 2508 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf