Search Results for "JVET-AO0173"

Found 5 document(s)

Search documents

Use number, keyword, author, or MPEG number. Filter by meeting when needed.

41st Meeting: by teleconference, CH, January 2026 2026-01-14 20:21
Abstract
This contribution proposes a hybrid framework that integrates end-to-end learned intra-frame compression (NLIC) methods with conventional compression techniques. The framework involves using NLIC-coded intra frames and VTM-coded inter frames. Furthermore, for each intra frame, the encoder decides whether to code it with NLIC or with VTM. Two sets of results are provided, depending on whether the NLIC was optimized by means of perceptual finetuning (PFT). With this hybrid framework, under the Random-Access configuration, the resulting BD-rates over NNVC-15.0 VTM (with NN tools off) anchor are reported to be as follows:
JVET-AO0173 [AHG11] A Hybrid Framework Integrating End-to-End Learned Intra-Frame Codec with Conventional Codec [N. Zou, A. B. Koyuncu, A. Hallapuro, F. Cricri, H. Zhang, J. Ahonen, M. M. Hannuksela (Nokia)]

This contribution proposes a hybrid framework that integrates end-to-end learned intra-frame compression (NLIC) methods with conventional compression techniques. The framework involves using NLIC-coded intra frames and VTM-coded inter frames. Furthermore, for each intra frame, the encoder decides whether to code it with NLIC or with VTM. Two sets of results are provided, depending on whether the NLIC was optimized by means of perceptual finetuning (PFT). With this hybrid framework, under the Random-Access configuration, the resulting BD-rates over NNVC-15.0 VTM (with NN tools off) anchor are reported to be as follows:

The system optimized with MSE and rate losses (no perceptual fine-tuning):

Overall -0.66% (Y), -2.90% (Cb), -1.31% (Cr)

Additionally, the Random-Access simulation results are evaluated with 8 perceptual metrics, the resulting perceptual BD-rates over NNVC-15.0 VTM (with NN tools off) anchor are reported to be as follows:

AVG

msssim Torch

Vif

Fsim

nlpd

iw-ssim

vmaf

psnrHVS

lpips

W/O PFT

-1.57%

-1.87%

-2.17%

-1.15%

-0.90%

-1.57%

-0.64%

-0.66%

-2.69%

W/ PFT

-5.59%

-8.48%

-4.57%

-3.33%

-3.18%

-6.91%

-1.16%

-1.24%

-11.49%

It was noted that there is no gain in AI – proponents explain that the model was not optimized for that case (models were optimized for different QP), such that the encoder always decides for VVC intra.

The algorithm is the same as in EE1-6.

It was asked what the...

Decisions
It was concluded to investigate this in EE1 in the context of the multi-layer interface.
Citation
42nd Meeting: Santa Eulària, ES, April 2026 2026-04-30 22:25
Abstract
This document summarizes Exploration Experiment 1 (EE1) tests to be performed between the JVET-AP and JVET-AR meetings to evaluate Neural Network-based Video Coding (NNVC) technologies, analyze their performances and complexity aspects.
JVET-AP2023 Exploration experiment on neural network-based video coding (EE1) [E. Alshina, R. Chang, F. Galpin, Yue Li, Yun Li, M. Santamaria, T. Shao, J. Ström, Z. Xie (EE coordinators)] (2026-05-15)

An initial draft of this document was reviewed and approved at 0910-0925 on Friday 1 May.

This round of EE1 tests includes:

  • EE1-1: LOP in-loop filter
    • EE1-1.1 – Dynamic convolution for LOP7 neural in-loop filtering JVET-AO0055 (KHU, KBS).
    • EE1-1.2 – AHG11: Enhancing LOP7 with Re-Exploited Boundary Strength Guidance JVET-AO0144 (HUST)
  • EE1-2: VLOP in-loop filter
    • EE1-2.1 – VLOP with new backbone block based on Spatial-Channel Mixing JVET-AO0129
  • EE1-3 NN-Inter
    • EE1-3.1 – Very Small Deep Reference Frame Generation Network for Inter Prediction Enhancement JVET-AO0267
  • EE1-4: Framework for externally coded pictures
    • EE1-4.1 - Multi-layer framework (as it is in NNVC-16, with residual coding)
    • EE1-4.2 - Multi-layer framework with frame level control (full replacement of VVC I-frame with E2E AI coded picture depending on picture level flag)
    • EE1-4.3 - Single-layer framework as proposed in JVET-AO0173 with different E2E AI codec
    • EE1-4.4 - Single-layer framework as proposed in JVET-AO0173 with frame level control (full replacement of VVC I-frame with E2E AI coded picture depending on picture level flag)
  • EE1-5: operational bit-exact reproducibility
    • EE1-5.1 –  [AHG11] Stable float convolution for neural network inference JVET-AO0178 (Nokia)
No output: JVET-Ax2024

JVET-AP2023 Exploration experiment on neural network-based video coding (EE1) [E. Alshina, R. Chang, F. Galpin, Yue Li, Yun Li,...

Decisions
JVET-AP2023 Exploration experiment on neural network-based video coding (EE1)
No output: JVET-Ax2024
Citation
41st Meeting: by teleconference, CH, January 2026 2026-02-10 18:43
Abstract
This document summarizes Exploration Experiment 1 (EE1) tests to be performed between the JVET-AO and JVET-AP meetings to evaluate Neural Network-based Video Coding (NNVC) technologies, analyze their performances and complexity aspects.
JVET-AO2023 Exploration experiment on neural network-based video coding (EE1) [E. Alshina, R. Chang, F. Galpin, Yue Li, Yun Li, M. Santamaria, T. Shao, J. Ström, Z. Xie (EE coordinators)] (2026-02-06)

An initial draft of this document was reviewed and approved at 1310-1335 on Friday 23 January.

This round of EE1 tests includes:

  • EE1-1: LOP in-loop filter
    • EE1-1.1 – Dynamic convolution for LOP7 neural in-loop filtering JVET-AO0055 (KHU, KBS).
    • EE1-1.2 – Combination test of EE1-1.1 and Backbone Block Enhancement of LOP In-Loop Filter with Over-Parameterized Training and Variable Channels JVET-AO0074 (Xidian Univ., UESTC, Transsion)
    • EE1-1.3 – AHG11: Enhancing LOP7 with Re-Exploited Boundary Strength Guidance JVET-AO0144 (HUST)
  • EE1-2: VLOP in-loop filter
    • EE1-2.1 – VLOP with new backbone block based on Spatial-Channel Mixing JVET-AO0129
  • EE1-3 NN-Inter
    • EE1-3.1 – Very Small Deep Reference Frame Generation Network for Inter Prediction Enhancement JVET-AO0267
  • EE1-4: Framework for externally coded pictures
    • EE1-4.1 - Multi-layer framework (as it is in NNVC-16, with residual coding)
    • EE1-4.2 - Multi-layer framework with frame level control (full replacement of VVC I-frame with E2E AI coded picture depending on picture level flag)
    • EE1-4.3 - Single-layer framework as proposed in JVET-AO0173 with different E2E AI codec
    • EE1-4.4 - Single-layer framework as proposed in JVET-AO0173 with frame level control (full replacement of VVC I-frame with E2E AI coded picture depending on picture level flag)
  • EE1-5: operational bit-exact reproducibility
    • EE1-5.1 – [AHG11] Stable float convolution for neural network...
Decisions
JVET-AO2023 Exploration experiment on neural network-based video coding (EE1)
EE1-5.1 – [AHG11] Stable float convolution for neural network inference JVET-AO0178 (Nokia)
Citation
41st Meeting: by teleconference, CH, January 2026 2026-02-05 12:07

Abstract not available in document

JVET-AO2041 Announcement of JVET AHG17 Meeting in Aachen, DE, 25-27 February 2026 The following 5 documents were produced as WG 5 documents only, without a corresponding JVET output document or direct repetition of their content in this meeting report: WG 5 N 384 Preliminary disposition of comments received on ISO/IEC 14496-10:2025/DAM 1 WG 5 N 385 Disposition of comments received on DIS ISO/IEC 23090-15:202X (3rd edition) WG 5 N 386 Disposition of comments received on ISO/IEC DTR 23888-3 WG 5 N 390 Liaison statement to ISO/IEC JTC 1/SC 29/WG 1 (JPEG) on JPEG AI and explorations on video coding WG 5 N 391 Liaison statement to SMPTE on requesting SEI mechanism for new SMPTE ST 2094-60 standard For the organization and planning of its future work, the JVET established 18 “ad hoc groups” (AHGs) to progress the work on particular subject areas. Another Joint AHG on Gaussian splat coding was...
Decisions
a) JVET documents
The meeting was closed at 2349 UTC on 2026-01-23.
Citation
41st Meeting: by teleconference, CH, January 2026 2026-01-14 16:51
Abstract
This document summarizes the activities of AHG11: Neural network-based video coding between the 40th meeting in Geneva and 41st on-line meeting.
JVET-AO0011 JVET AHG report: Neural network-based video coding (AHG11) [E. Alshina, F. Galpin, S. Liu (co-chairs), J. Li, Y. Li, R.-L. Liao, M. Santamaria, T. Shao, M. Wien, P. Wu (vice chairs)] Activities The AHG used the main JVET reflector, jvet@lists.rwth-aachen.de, for emails exchange. Teleconferences The AHG conducted two joint teleconferences with AHG14 and EE1 during the interim period. The teleconferences were held on November, 18 and December, 16. In those teleconferences, the following topics were discussed: NNVC15.0 software integration status and anchor performance. Hybrid plus E2E AI video codec framework development status report. MPEG AI survey. Training reproducibility Overflow aware model quantizing for bit-exact reproducibility EE1 tests final design. Details are summarized in the AHG11 & AHG14 teleconference report JVET-AO0041. Common Test Conditions The anchor for th...
Decisions
The AHG recommended to: Review all input contributions. Continue investigating neural network-based video coding tools, including coding performance and complexity. Continue study of the framework for hybrid codec combined with End-to-End AI coded pictures. Discuss device interoperability and bit-exact reconstruction of NNVC algorithms. Recommend promising technologies for next EE1 round.
Citation
New Search