(Visual) Data Compression

Data compression is a ubiquitous aspect of modern computing, and particularly important when dealing with video data as this type of data largely dominates global IP traffic. Visual data has evolved drastically away from traditional 2D images and video: current sensor technologies capture reality in unprecedented detail, leading to a high variety in modalities, such as HDR content, 360° video, hyperspectral imaging, point clouds (e.g., from 3D scanners), or light field data (e.g., from plenoptic cameras). Besides this, there is also a larger variety in display/visualization technologies, such as auto-stereoscopic screens, multi-view screens, HMDs, immersive 3D projection systems, or even holographic displays. The result is that one no longer just renders the signal that was captured (which is the case with 2D video coding), and that visual data needs to be processed between capturing and rendering, something that is often coined “computational imaging”.

 

IDLab-MEDIA has an internationally recognized long-standing tradition in video coding as being member of several standardization committees such as MPEG, VQEG, JVT/JCT-VC (H.264/AVC, HEVC, and VVC).  Currently, IDLab-MEDIA is very active in the compression of video, light fields (images and video), image-based virtual reality, and 3D meshes.

 

 

  • 2021 IEEE Multimedia Prize Paper Award for SMoE Light Field Technology July 9, 20212021 IEEE Multimedia Prize Paper Award for SMoE Light Field Technology
    We’re happy and honored to announce that our light field technology paper “Steered Mixture-of-Experts for Light Field Images and Video: Representation and Coding” has been rewarded with the 2021 IEEE Multimedia Prize Paper Award. This is an annual award for one original paper in the field of multimedia published in the IEEE Transactions of Multimedia ...
  • Keyframe Insertion: Enabling Low-Latency Random Access and Packet Loss Repair February 11, 2021Keyframe Insertion: Enabling Low-Latency Random Access and Packet Loss Repair
    From a video coding perspective, there are two challenges when performing live video distribution over error-prone networks, such as wireless networks, namely random access and packet loss repair. There is a scarceness of solutions that do not impact steady state usage and users with reliable connections. The proposed solution minimizes this impact by complementing a ...
  • Funding granted for imec.icon LIVE-G July 23, 2020Funding granted for imec.icon LIVE-G
    LIVE-G – Low-latency Video over 5G Mobile connectivity is currently stepping into the fifth-generation wireless network (5G) wave. 5G technology promises significant improvements compared to its 3G/4G predecessors such as reduced network congestion, higher and more reliable bandwidths and significantly lower network delays. 5G will be better suited for mission-critical communications, massive Internet-of-Things connectivity, immersive video/AR/VR ...
  • Funding granted for Interdisciplinary Research Project on computer vision and intelligent mowing patterns to automate biodiversity management in grasslands June 18, 2020Funding granted for Interdisciplinary Research Project on computer vision and intelligent mowing patterns to automate biodiversity management in grasslands
    This project aims to deliver a unique, novel and first-ever approach to incorporate AI-technology in order to contribute to the biodiversity in our nature. More specifically, automated biologically optimised mowing strategies guided by computer vision and AI algorithms will be developed for the sustainable management of grasslands. The research performed in this project will aid the ...
  • Paper accepted in MTAP: Random Access Prediction Structures for Light Field Video Coding with MV-HEVC May 26, 2020Paper accepted in MTAP: Random Access Prediction Structures for Light Field Video Coding with MV-HEVC
    Our article with the title “Random access prediction structures for light field video coding with MV-HEVC” was published in Multimedia Tools and Applications. The article focuses on exploring prediction structures that can enable random access when compressing light field video with MV-HEVC. Light field video promises to deliver the required six degrees of freedom (6DoF) ...
  • PhD: Towards Image-Based Virtual Reality using Kernel-Based Representations May 1, 2020PhD: Towards Image-Based Virtual Reality using Kernel-Based Representations
    On April 28th, 2020, Ruben Verhack (IDLab-MEDIA) successfully defended his joint PhD in an entirely virtual setting. This joint PhD is a collaboration between the Communication Systems Lab, TU Berlin and IDLab, Ugent. This research was performed under the supervision of Prof. Peter Lambert (Ugent) and Prof. Thomas Sikora (TU Berlin) Steered Mixture-of-Experts for ...
  • PhD: Light Field Image and Video Coding for Immersive Media March 18, 2020PhD: Light Field Image and Video Coding for Immersive Media
    Belgium declared a lockdown for the entire country as a result of the COVID-19 crisis on Wednesday (18 March), following the example of several European countries. A couple of hours later, Vasileios Avramelos from IDLab-MEDIA group was the first member of our faculty to publicly defend his PhD thesis in a 100% virtual online setting. ...
  • Paper Accepted at IEEE ICCE-Berlin 2019: Light Field Image Compression Using Versatile Video Coding (VVC) September 8, 2019Paper Accepted at IEEE ICCE-Berlin 2019: Light Field Image Compression Using Versatile Video Coding (VVC)
    Our research paper on light field image compression using the upcoming video coding standard VVC (Versatile Video Coding) has been accepted for presentation at the IEEE International Conference on Consumer Electronics in Berlin, Germany. Light field cameras (or plenoptic cameras) made it possible to not only capture information about the light intensity in a scene, but ...
  • Paper presented at SPIE optics + photonics 2019 August 14, 2019Paper presented at SPIE optics + photonics 2019
    An overview research paper on multi-view HEVC (MV-HEVC) prediction structures for light field video compression was presented during the 2019 SPIE optics + photonics international conference in San Diego, CA. Light field video is a promising technology for delivering the required six-degrees-of-freedom for natural content in virtual reality. Already existing multi-view coding (MVC) and multi-view ...
  • Article accepted for publication in the Journal of Real-Time Image Processing: Pixel-level parallel rendering for images and light fields December 9, 2018Article accepted for publication in the Journal of Real-Time Image Processing: Pixel-level parallel rendering for images and light fields
    Our article with the title “Highly Parallel Steered Mixture-of-Experts Rendering at Pixel-level for Image and Light Field Data” was recently accepted for publication in the Journal of Real-Time Image Processing. In the specific article we describe our novel image approximation framework namely Steered Mixture-of-Experts (SMoE) and its potential capabilities in coding and streaming higher dimensional image ...

View all posts