JVET-AM0008 JVET AHG report: Optimization of encoders and receiving systems for machine analysis of coded video content (AHG8) [S. Liu, J. Ström, S. Wang, M. Zhou (AHG chairs)]
Software and Common Test Conditions
AHG 8 related software and documents can be accessed at https://vcgit.hhi.fraunhofer.de/jvet-ahg-ofm. This repository contains two projects: common test conditions, reporting templates with anchor results, evaluation scripts and task networks are available in https://vcgit.hhi.fraunhofer.de/jvet-ahg-ofm/ofm-ctc, and software implementation examples are hosted in https://vcgit.hhi.fraunhofer.de/jvet-ahg-ofm/vtm-ofm. For this meeting cycle, common test conditions remain unchanged as described in output document JVET-AI2031.
Technical Report
The 9th draft of the technical report (TR) JVET-AL2030 “Optimization of encoders and receiving systems for machine analysis of coded video content (draft 9)” was produced and uploaded to JVET document system on 2025-04-30, including the following additions on top of draft 8:
- Updated to address comments in m72107
- Tool combination example (to Annex B) JVET-AL0152
The following combined tool examples have been included in the submitted DTR, besides single tool implementation examples.
Technology 1 | Technology 2 | Technology 3 | Technology 4 | Technology 5 |
Adaptive QP (8.1 and A.1) | Temporal layer QP offset (8.2) | |||
De-noising filter (7.5) | Temporal layer QP offset (8.2) | |||
Pre-processing (7.2 and A.2) | NNPF (9.3 and A.3) | |||
4:4:4 coding (8) | Reduced resolution (Clauses 7.4 and 9.2) | |||
Pre-processing (7.2 and A.2) | NNPF (9.3 and A.3) | Adaptive QP (8.1 and A.1) | ||
NNPF (9.3 and A.3) | Adaptive QP (8.1 and A.1) | |||
NNPF (9.3 and A.3) | Reduced resolution (Clauses 7.4 and 9.2) | |||
Pre-processing (7.2 and A.2) | NNPF (9.3 and A.3) | Adaptive QP (8.1 and A.1) | Temporal layer QP offset (8.2) | |
Pre-processing (7.2 and A.2) | NNPF (9.3 and A.3) | Adaptive QP (8.1 and A.1) | Temporal resampling (9.1 and A.4) | |
Pre-processing (7.2 and A.2) | NNPF (9.3 and A.3) | Adaptive QP (8.1 and A.1) | Temporal resampling (9.1 and A.4) | Temporal layer QP offset (8.2) |
Input contributions
There were no input contributions related to AHG 8 mandates (by the time the AHG report was uploaded) except the report itself.
Recommendations
The AHG recommended to:
- Continue improving the on-going TR document based on feedback.
- Discuss plan and timeline for finalization of TR (version 1).
- Continue investigating non-normative technologies and their uses for machine vision applications and machine consumptions.