Soheib Takhtardeshir
Doktorand|Doctoral Student
- Professional title: Doctoral Student
- Academic title: Doctoral Student
- Telephone: +46 (0)10-1726585
- Email: soheib.takhtardeshir@miun.se
- Room number: Ej Angivet
- Location: Sundsvall
-
- Employed at the subject:
- Computer Engineering
-
- Research centers:
- STC Research Centre
Ph.D. Student in Computer Engineering
My name is Soheib Takhtardeshir, and I am from Sanandaj, Iran. I am an Early Stage Researcher in the Realistic3D lab under the Information System and Technology Department. My Ph.D. supervisors are Prof. Mårten Sjöström and Prof. Christine Guillemot . My project title is "Representation and compression of multi-sensor video for combined human and computer vision applications".
Background
I started my bachelor’s in Electrical engineering in 2009 and, completed it in 2013. After that, I joined FiberHome International Co. as a technical engineer in 2015. In 2019, I decided to continue my studies, and I was accepted as a master’s student in Digital electronic engineering. I finished my master’s in 2021 and I started my Ph.D at Mid Sweden University in 2022.
Area of interest
Image and Video Compression, Plenoptics, Machine Learning, Deep Learning, Digital Image Processing, Computer Vision
Publications
Articles in journals
Conference papers
Doctoral theses, comprehensive summaries
Other
Articles in journals
Takhtardeshir, S. , Olsson, R. , Guillemot, C. & Sjöström, M. (2026). DUALF-D : Disentangled dual-hyperprior approach for light field image compression. Signal processing. Image communication, vol. 140
Takhtardeshir, S. , Olsson, R. , Guillemot, C. & Sjöström, M. (2025). Efficient and Fast Light Field Compression via VAE-Based Spatial and Angular Disentanglement. IEEE Access, vol. 13, pp. 18594-18607.
Conference papers
Takhtardeshir, S. , Olsson, R. , Guillemot, C. & Sjöström, M. (2025). DUALF-C: Disentangled Light Field Compression with Entropy-Aware Bitstream Generation. Paper presented at the Visual Communications and Image Processing (VCIP 2025) Conference, Klagenfurt, Austria, December 1-4, 2025
Zerman, E. , Takhtardeshir, S. , Trioux, A. , Qin, J. , Wu, W. , Olsson, R. & Sjöström, M. (2025). Subjective Visual Quality Assessment of Compressed Light Field Images : Learning-based vs. Conventional Methods. Paper presented at the International Workshop on Multimedia Signal Processing (MMSP)
Takhtardeshir, S. , Olsson, R. , Guillemot, C. & Sjöström, M. (2024). A Deep Learning based Light Field Image Compression as Pseudo Video Sequences with Additional in-loop Filtering. In 3D Imaging and Applications 2024-Electronic Imaging. San Francisco Airport in Burlingame, California : . pp. 1--6.
Zerman, E. , Gond, M. , Takhtardeshir, S. , Olsson, R. & Sjöström, M. (2024). A Spherical Light Field Database for Immersive Telecommunication and Telepresence Applications. Paper presented at the 2024 16th International Conference on Quality of Multimedia Experience (QoMEX)
Eslami, M. R. , Takhtardeshir, S. , Sharif, S. & Banad, Y. M. (2024). Hardware Implementation of Memristor-Based in-Memory Computing for Classification Tasks. In 2024 IEEE 67th International Midwest Symposium on Circuits and Systems (MWSCAS).. pp. 126--130.
Doctoral theses
Takhtardeshir, S. (2026). VAE-Based Compression of Light Field Images Using Disentangled Latent Modeling and Perceptual Quality Assessment. Dis. (Comprehensive summary) Sundsvall : Mid Sweden University, 2026 (Mid Sweden University doctoral thesis : 440) (École Doctoral: Centre Inria de l’Université de Rennes : 601)
Other
Zerman, E. , Takhtardeshir, S. , Trioux, A. , Olsson, R. & Sjöström, M. (2025). MiX-LFQDB: MIUN-Xidian Light Field Quality Database for Compressed Light Field Images using Learning-based vs. Conventional Methods.
Zerman, E. , Gond, M. , Takhtardeshir, S. , Olsson, R. & Sjöström, M. (2024). A New Spherical Light Field Database for Immersive Telecommunication and Telepresence Applications.