Efficient and Fast Light Field Compression via VAE-Based Spatial and Angular Disentanglement
Light field (LF) imaging captures both spatial and angular information, which is essential for applications such as depth estimation, view synthesis, and post-capture refocusing. However, the efficient processing of this data, particularly in terms of compression and encoding/decoding time, presents...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10849543/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576745435299840 |
|---|---|
| author | Soheib Takhtardeshir Roger Olsson Christine Guillemot Marten Sjostrom |
| author_facet | Soheib Takhtardeshir Roger Olsson Christine Guillemot Marten Sjostrom |
| author_sort | Soheib Takhtardeshir |
| collection | DOAJ |
| description | Light field (LF) imaging captures both spatial and angular information, which is essential for applications such as depth estimation, view synthesis, and post-capture refocusing. However, the efficient processing of this data, particularly in terms of compression and encoding/decoding time, presents challenges. We propose a Variational Autoencoder (VAE)-based framework to disentangle the spatial and angular features of light field images, focusing on fast and efficient compression. Our method uses two separate sub-encoders—one for spatial and one for angular features—to allow for independent processing in the latent space, which facilitates more streamlined compression workflows. Evaluations on standard light field datasets demonstrate that our approach reduces encoding and decoding time significantly, with a slight trade-off in Rate-Distortion (RD) performance, making it suitable for real-time applications. |
| format | Article |
| id | doaj-art-349dcd44d1c644f3ad1776393494131e |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-349dcd44d1c644f3ad1776393494131e2025-01-31T00:00:50ZengIEEEIEEE Access2169-35362025-01-0113185941860710.1109/ACCESS.2025.353260810849543Efficient and Fast Light Field Compression via VAE-Based Spatial and Angular DisentanglementSoheib Takhtardeshir0https://orcid.org/0009-0008-5477-0920Roger Olsson1Christine Guillemot2https://orcid.org/0000-0003-1604-967XMarten Sjostrom3https://orcid.org/0000-0003-3751-6089Department of Computer and Electrical Engineering, Mid Sweden University, Sundsvall, SwedenDepartment of Computer and Electrical Engineering, Mid Sweden University, Sundsvall, SwedenINRIA, Rennes, FranceDepartment of Computer and Electrical Engineering, Mid Sweden University, Sundsvall, SwedenLight field (LF) imaging captures both spatial and angular information, which is essential for applications such as depth estimation, view synthesis, and post-capture refocusing. However, the efficient processing of this data, particularly in terms of compression and encoding/decoding time, presents challenges. We propose a Variational Autoencoder (VAE)-based framework to disentangle the spatial and angular features of light field images, focusing on fast and efficient compression. Our method uses two separate sub-encoders—one for spatial and one for angular features—to allow for independent processing in the latent space, which facilitates more streamlined compression workflows. Evaluations on standard light field datasets demonstrate that our approach reduces encoding and decoding time significantly, with a slight trade-off in Rate-Distortion (RD) performance, making it suitable for real-time applications.https://ieeexplore.ieee.org/document/10849543/Light fieldcompressiondisentanglingvariational auto-encoder |
| spellingShingle | Soheib Takhtardeshir Roger Olsson Christine Guillemot Marten Sjostrom Efficient and Fast Light Field Compression via VAE-Based Spatial and Angular Disentanglement IEEE Access Light field compression disentangling variational auto-encoder |
| title | Efficient and Fast Light Field Compression via VAE-Based Spatial and Angular Disentanglement |
| title_full | Efficient and Fast Light Field Compression via VAE-Based Spatial and Angular Disentanglement |
| title_fullStr | Efficient and Fast Light Field Compression via VAE-Based Spatial and Angular Disentanglement |
| title_full_unstemmed | Efficient and Fast Light Field Compression via VAE-Based Spatial and Angular Disentanglement |
| title_short | Efficient and Fast Light Field Compression via VAE-Based Spatial and Angular Disentanglement |
| title_sort | efficient and fast light field compression via vae based spatial and angular disentanglement |
| topic | Light field compression disentangling variational auto-encoder |
| url | https://ieeexplore.ieee.org/document/10849543/ |
| work_keys_str_mv | AT soheibtakhtardeshir efficientandfastlightfieldcompressionviavaebasedspatialandangulardisentanglement AT rogerolsson efficientandfastlightfieldcompressionviavaebasedspatialandangulardisentanglement AT christineguillemot efficientandfastlightfieldcompressionviavaebasedspatialandangulardisentanglement AT martensjostrom efficientandfastlightfieldcompressionviavaebasedspatialandangulardisentanglement |