Search Results for "JVET-M0526"
Found 3 document(s)
Search documents
Use number, keyword, author, or MPEG number. Filter by meeting when needed.
Not signed in yet.
Abstract
At the 11th JVET meeting, alternative temporal motion vector prediction (ATMVP) was adopted to VTM reference software. Aiming at reducing both the average and worst-case complexity, this contribution proposes a simplification of ATMVP co-located block derivation process in the case of bidirectional prediction. Simulation results for the simplification show no performance change compared to VTM-3.0 and observe minor encoding and decoding time decrease.
Loading full meeting notes...
JVET-M0526 CE2-related: Further simplification of ATMVP collocated block derivation [S. H. Wang (Peking Univ.), X. Zheng (DJI), S. S. Wang, S. W. Ma (Peking Univ.)] [late]
Initial upload rejected as placeholder
Cited:
Decisions
rejected
Initial upload rejected as placeholder
Citation
Abstract
The cross-check results in the input document JVET-M0526: CE2-related: Further simplification of ATMVP collocated block derivation are investigated in this report. The contribution reports results on the average and worst-case complexity reduction for ATMVP by disabling the reference list loop during the derivation of the co-located block in the case of bi-directional prediction. The cross-check validated the experimental results from the ATMVP simplifications.
Loading full meeting notes...
JVET-M0602 Cross-check of JVET-M0526: CE2-related: Further simplification of ATMVP collocated block derivation [S. Bandyopadhyay (InterDigital)] [late]
References:
Decisions
JVET-M0602 Cross-check of JVET-M0526: CE2-related: Further simplification of ATMVP collocated block derivation [S. Bandyopadhyay (InterDigital)] [late]
Citation
Abstract
The purpose of this Core Experiment (CE) is to investigate the coding tools related to neural network (NN) based loop filter on top of the Test Model. In this CE, the impact of the position of the NN based filter in the filter chain, the benefit of the CTU level NN filter adaptive on/off switching, and the generalization capability when QP is different from the training QP will be investigated. In addition to the encoder and decoder run-times, the network information, e.g., network parameter numbers, number of layers, and convolution kernel size will also be evaluated. The list of tools and experiments to be performed are detailed in this document.
Loading full meeting notes...
JVET-M1033 Description of Core Experiment 13 (CE13): Neural-network based loop filtering [Y. Li, S. Liu, K. Kawamura]
Future meeting plans, expressions of thanks, and closing of the meeting
Future meeting plans were established according to the following guidelines:
- Meeting under ITU-T SG 16 auspices when it meets (starting meetings on the Tuesday of the first week and closing it on the Wednesday of the second week of the SG 16 meeting – a total of 9 meeting days), and
- Otherwise meeting under ISO/IEC JTC 1/SC 29/WG 11 auspices when it meets (starting meetings on the Wednesday prior to such meetings and closing it at lunchtime on the last day of the WG 11 meeting – a total of 9.5 meeting days).
In cases where an exceptionally high workload is expected for a meeting, an earlier starting date may be defined.
Some specific future meeting plans (to be confirmed) were established as follows:
- Tue. 19 – Wed. 27 March 2019, 14th meeting under ITU-T auspices in Geneva, CH.
- Wed. 3 – Fri. 12 July 2019, 15th meeting under WG 11 auspices in Gothenburg, SE.
- Tue. 1 – Wed. 9 October 2019, 16th meeting under ITU-T auspices in Geneva, CH.
- Wed. 8 – Fri. 17 January 2020, 17th meeting under WG 11 auspices in Brussels, BE.
The agreed document deadline for the 14th JVET meeting was planned to be Tuesday 12 March 2019. Plans for scheduling of agenda items within that meeting remained TBA.
WG 11, the local hosting organization Ecole Mohammadia d’Ingénieurs (EMI) – Mohammed V University, Rabat, Morocco, and Abdellatif Benjelloun Touimi were thanked for the excellent hosting and organization of the 13th ...
Decisions
Jian Qing Zhu (Fujitsu R&D Center)
Citation