Search Results for "JVET-AO0173"
Found 5 document(s)
Use number, keyword, author, or MPEG number. Filter by meeting when needed.
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...
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,...
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...
Abstract not available in document