MPAI calls for Up-sampling Filter for Video application technologies

MPAI-50 has published the Call for Technologies: Up-sampling Filters for Video applications (MPAI-UFV) V1.0 requesting parties having rights to technologies satisfying the Use Cases and Functional Requirements and the Framework Licence of the planned Technical Specification: Up-sampling Filter for Video Applications (MPAI-UFV) V1.0 to respond to this Call for Technologies preferably using the Template for responses.

The goal of MPAI-UFV V1.0 is to develop a standard up-sampling filter that provides optimal performance when applied to a video to generate a video with a higher number of lines and pixels.

The submissions received will be assessed, collaboratively improved, if found suitable, and used in the development of the planned MPAI-UFV Technical Specification.

MPAI membership is not a prerequisite for responding to this Call for Technologies. However, if a (part of a) submission that is accepted for inclusion in the planned MPAI-UFV TS, the Proponent must join MPAI, or lose the opportunity to have the accepted technologies included in the TS.

MPAI will select the most suitable technologies based on their technical merits. However, MPAI is not obligated to select a particular technology or any of the proposed technologies if those submitted are found to be inadequate.

Proponents shall mandatorily:

1. Submit a complete description of the proposed up-sampling filter with a level of detail allowing an expert in the field to develop and implement the proposed filter.
2. Upload the following software to the MPAI storage:
   1. Docker image that contains the encoding and decoding environments, encoder, decoder, and bitstreams.
   2. Up-sampling filter in source code (preferred) or executable form. Note that proponents of accepted proposals will be requested to provide the source code of the up-sampling filter.
   3. Python scripts to enable testers to carry out the Performance Test.
3. Submit the following results:
   1. Tables of objective quality results obtained by the submitter with their proposed solution.
   2. The decoded Test Sequences.
   3. The up-sampling results for SD to HD and HD to 4K obtained with the proposed solution.
   4. The VMAF-BD Rate assessment provided with a graph for each QP and a table with minimum, maximum and average value for each sequence.
   5. A Complexity assessment using MAC/pixel and number of parameters of the submitted up-sampling filter. Use of SADL (6) is recommended.

Submissions will be evaluated by an Evaluation Team created from:

1. MPAI Member representatives in attendance.
2. Non-MPAI Member representatives who are respondents to any of the received submissions.
3. Non respondent experts/non MPAI Member representatives invited in a consulting capacity.
4. No one from 1. and 2. will be denied membership in the Evaluation Panel if they request it.

Submissions will be evaluated by an Evaluation Team created from:

1. MPAI Member representatives in attendance.
2. Non-MPAI Member representatives who are respondents to any of the received submissions.
3. Non respondent experts/non MPAI Member representatives invited in a consulting capacity.
4. No one from 1. and 2. will be denied membership in the Evaluation Panel if they request it.

Proposals will be assessed using the following process:

1. The objectively computed Quality Tests will use the Test Sequences provided to MPAI by an independent academic after the proposal deadline and distributed to Respondents.
2. Each Respondent presents their proposal.
3. Evaluation Team members ask questions.
4. Evaluation Team organises the Tests.
5. A volunteer member of the Evaluation Team executes the docker image of a Respondent and computes the values obtained using the test set provided by the respected academic.
6. The Objective Quality Evaluation will use the VMAF-BD Rate metrics to compare the sequences obtained by up-sampling with the bicubic filter the AVC, HEVC and VVC co-decoded with QP Values: 22, 27, 32, 37, 42 with the same co-decoded sequences up-sampled with the proposed up-sampling algorithm.
7. Latency is the number of frames used by the up-sampling process. Note that the actual number of frames used to produce the response should be specified.
8. The Complexity evaluation will use MAC/pixel and number of parameters.

The timeline of proposal submission is:

Those intending to propose should become familiar with the four documents mentioned above and posted here. An online presentation will be made on 2024/11/27 at 14UTC. Register at https://bit.ly/3V0sdt1 to attend.