VSVida Fakour Sevom

Vida Fakour Sevom

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Vida Fakour Sevom has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Video coding of dynamic 3D point cloud data

    by Sebastian Schwarz, Nahid Sheikhipour, Vida Fakour Sevom, Miska M. Hannuksela

    Due to the increased popularity of augmented (AR) and virtual (VR) reality experiences, the interest in representing the real world in an immersive fashion has never been higher. Distributing such representations enables users all over the world to freely navigate in never seen before media experiences. Unfortunately, such representations require a large amount of data, not feasible for transmission on today's networks. Thus, efficient compression technologies are in high demand. This paper proposes an approach to compress 3D video data utilizing 2D video coding technology. The proposed solution was developed to address the needs of “tele-immersive” applications, such as VR, AR, or mixed reality with “Six Degrees of Freedom” capabilities. Volumetric video data is projected on 2D image planes and compressed using standard 2D video coding solutions. A key benefit of this approach is its compatibility with readily available 2D video coding infrastructure. Furthermore, objective and subjective evaluation shows significant improvement in coding efficiency over reference technology. The proposed solution was contributed and evaluated in international standardization. Although it is was not selected as the winning proposal, as very similar solution has been selected developed since then.


  • Geometry-Guided 3D Data Interpolation for Projection-Based Dynamic Point Cloud Coding

    by Vida Fakour Sevom, Sebastian Schwarz, Moncef Gabbouj

    With the recent improvements in acquisition techniques for 3D media applications, it has become easier to collect 3D data, for example, dynamic point cloud data. Such point clouds consist of a large amount of 3D coordinates, which describe a scene or object in 3D space by its geometry and texture attributes. Moreover, they are an effective representation of 3D environments for applications such as Augmented Reality or Virtual Reality. One of the main problems for such data is that the number of points is typically too large to allow for real-time transmission or efficient storage. Thus, compressing such 3D data is a key issue to reduce the amount of required bandwidth or memory. This paper presents a method for efficient compression of dynamic point cloud data within the current MPEG standardization framework for dynamic point cloud compression. The key benefit of the presented work is the reduced number of encoded and decoded 3D points compared to the reference framework, thus encoding and decoding complexity is reduced significantly. Objective results show a speed-up of around 35-40% in coding times. Furthermore, reconstruction quality is preserved, thus reducing bit rate requirements by up to 30%. Visual results verify the improved reconstruction quality, and compared to the reference at the same computational complexity, coding efficiency is improved by over 40%.


  • 2D Video Coding of Volumetric Video Data

    by Sebastian Schwarz, Miska M. Hannuksela, Vida Fakour-Sevom, Nahid Sheikhi-Pour

    Due to the increased popularity of augmented and virtual reality experiences, the interest in representing the real world in an immersive fashion has never been higher. Distributing such representations enables users all over the world to freely navigate in never seen before media experiences. Unfortunately, such representations require a large amount of data, not feasible for transmission on today's networks. Thus, efficient compression technologies are in high demand. This paper proposes an approach to compress 3D video data utilizing 2D video coding technology. The proposed solution was developed to address the needs of `tele-immersive' applications, such as virtual (VR), augmented (AR) or mixed (MR) reality with Six Degrees of Freedom (6DoF) capabilities. Volumetric video data is projected on 2D image planes and compressed using standard 2D video coding solutions. A key benefit of this approach is its compatibility with readily available 2D video coding infrastructure. Furthermore, objective and subjective evaluation shows significant improvement in coding efficiency over reference technology.


  • Open Access

    360 Panorama Super-resolution using Deep Convolutional Networks

    by Vida Fakour-Sevom, Esin Guldogan, Joni-Kristian Kämäräinen


  • FPGA implementation and integration of a reconfigurable CAN-based co-processor to the coffee risc processor

    by Farid Shamani, Vida Fakour Sevom, Tapani Ahonen, Jari Nurmi

    This paper presents the design, implementation and integration of a reconfigurable Intellectual Property (IP)-based co-processor for the COFFEE RISC processor on a Field Programmable Gate Array (FPGA) device. The co-processor is capable of communicating with peripheral devices through the Controller Area Network (CAN) protocol. Although the main target of the co-processor is standard CAN frames, it is able to reconfigure itself in run-time to receive and decode the extended CAN frames. One of the main advantages of the co-processor is full compatibility with the COFFEE processor's requirements. Furthermore, the data transmission between the core and co-processor introduces no workload on the main data bus. In this implementation, the co-processor could achieve the maximum operating frequencies of 493MHz up to 825MHz in slow and fast timing models, respectively. As a result, the implemented co-processor gains (at least) 2.8x speed-up in comparison with the COFFEE processor by consuming a trivial dynamic energy. The ultimate achievement of this work is the new horizon expanded to the COFFEE processor to communicate with CAN-based peripheral devices which makes the core more versatile even for industrial purposes.

  • Design, implementation and analysis of a run-time configurable Memory Management Unit on FPGA

    by Farid Shamani, Vida Fakour Sevom, Jari Nurmi, Tapani Ahonen

    In this paper, we describe the design of a configurable Memory Management Unit (MMU) and its prototype implementation on a Field Programmable Gate Array (FPGA). We present analytical results of scaling the size of the second level software-managed Unified Translation Lookaside Buffer (UTLB) in terms of effect on the overall hit rate. Three design-time configurations with 16, 32, and 64 entries were used for this study. Critical path analysis of the logical design running on Altera Stratix-V FPGA is presented together with a description of optimization techniques employed in order to improve static timing performance. These optimization techniques assist in reaching 22.75% speed-up compared to non-optimized design. Moreover, maximum operating frequencies of 265, 225 and 200 MHz were achieved for UTLB sizes of 16, 32, and 64 entries, respectively. We quote worst case energy consumption figures with random input stimuli together with FPGA resource utilization characteristics for the above mentioned configurations. For resource-constrained or speed-critical hardware designs the 32-entry UTLB configuration provides a decent trade-off while the 16-entry configuration poses unsatisfactory performance. However, our target operating frequency of 200 MHz was eventually reached also for the 64-entry UTLB and hence it is our preferred option for most instantiations.