January 31st, 2017
Update: Paper submission due May 17th
This Challenge intends to identify technology that improves compression beyond the current state of the art in video compression, the most recent standard HEVC. Video compression continues to be one of the most important areas in image and signal processing, with more efficient binary representation needed due to the ever increasing amount and resolution of video data.
Participants are asked to deliver bitstreams with pre-defined maximum target rates for a given set of sequences, and a decoder executable for reconstructing the decoded videos. A paper could optionally be submitted as well, to be included for publication in the ICIP proceedings after passing peer review. The best performers will have the opportunity to present a summary of the underlying technology during the ICIP session where the results will be presented.
Furthermore, the best submission involving students’ work will be awarded a prize which is sponsored by Netflix.
Two sets of test sequences will be used, each to be encoded at four rate points. To be evaluated, it is mandatory to submit a full set of results for at least one of the sets:
Certain rules will be imposed on the submitted technology, such as
If specific mechanisms of rate control, and multipass/lookahead decisions are used during coding, they should be properly documented.
Objective criteria will be computed over the entire set of data to determine rate savings and quality improvements that are achieved. A software package for computing metrics, including PSNR, SSIM and VQM, will be provided to the participants.
Furthermore, formal subjective tests will be executed on selected test cases, to determine the visual performance. The exact methodology will be defined after receiving the submissions.
The Grand Challenge is organized by the following team:
This project has received funding from the European Union’s Seventh Framework Programme for research, technological development and demonstration under grant agreement no 608231
PROVISION Initial Training Network
Fraunhofer Heinrich Hertz Institute, Einsteinufer 37, 10587 Berlin, Germany