English
NEVC1.0 / README.md
nielsr's picture
nielsr HF Staff
Add pipeline tag, paper link, and abstract to model card for EHVC
d1beb69 verified
|
raw
history blame
7.77 kB
metadata
language:
  - en
license: bsd-3-clause-clear
pipeline_tag: video-to-video

NEVC-1.0
(EHVC: Efficient Hierarchical Reference and Quality Structure for Neural Video Coding)

📄 Paper

Performance comparison

📝 Introduction

This repository provides the pretrained model weights for NEVC-1.0, which integrates contributions from EHVC (Efficient Hierarchical Reference and Quality Structure for Neural Video Coding) — one of the core components of the framework.
EHVC introduces a hierarchical reference and quality structure that significantly improves both compression efficiency and rate–distortion performance.
The corresponding code repository can be found here: NEVC-1.0-EHVC.

📄 Paper Abstract

Neural video codecs (NVCs), leveraging the power of end-to-end learning, have demonstrated remarkable coding efficiency improvements over traditional video codecs. Recent research has begun to pay attention to the quality structures in NVCs, optimizing them by introducing explicit hierarchical designs. However, less attention has been paid to the reference structure design, which fundamentally should be aligned with the hierarchical quality structure. In addition, there is still significant room for further optimization of the hierarchical quality structure. To address these challenges in NVCs, we propose EHVC, an efficient hierarchical neural video codec featuring three key innovations: (1) a hierarchical multi-reference scheme that draws on traditional video codec design to align reference and quality structures, thereby addressing the reference-quality mismatch; (2) a lookahead strategy to utilize an encoder-side context from future frames to enhance the quality structure; (3) a layer-wise quality scale with random quality training strategy to stabilize quality structures during inference. With these improvements, EHVC achieves significantly superior performance to the state-of-the-art NVCs. Code will be released in: this https URL .

Key designs of EHVC include:

  • Hierarchical multi-reference: Resolves reference–quality mismatches using a hierarchical reference structure and a multi-reference scheme, optimized for low-delay configurations.
  • Lookahead mechanism: Enhances encoder-side context by leveraging forward features, thereby improving prediction accuracy and compression.
  • Layer-wise quantization scale with random quality training: Provides a flexible and efficient quality structure that adapts during training, resulting in improved encoding performance.

🔧 Models

EHVC uses two models: the intra model and the inter model.

  • The intra model handles intra-frame coding.
  • The inter model is responsible for inter-frame (predictive) coding.

Intra Model

The main contributions of NEVC-1.0 focus on inter coding.
For intra coding, we directly adopt the pretrained model cvpr2023_image_psnr.pth.tar from DCVC-DC, without further training.

Inter Model

The inter model of NEVC-1.0 is provided at /models/nevc1.0_inter.pth.tar.
The architecture of the inter model is illustrated below:

Inter model architecture

📊 Experimental Results

Objective Comparison

BD-Rate (%) comparison for PSNR
Anchor: VTM-23.4 LDB.
All codecs tested with 96 frames and intra-period = 32.

BD-Rate 96F32G

Rate–Distortion curves on HEVC B, HEVC C, UVG, and MCL-JCV datasets.
Tested with 96 frames and intra-period = 32.

RD curves 96F32G

BD-Rate (%) comparison for PSNR
Anchor: VTM-23.4 LDB.
All codecs tested with full sequences and intra-period = -1.

BD-Rate allF-1G

Rate–Distortion curves on HEVC B, HEVC C, UVG, and MCL-JCV datasets.
Tested with full sequences and intra-period = -1.

RD curves allF-1G

📜 Citation

If you find NEVC-1.0 useful in your research or projects, please cite the following paper:

  • EHVC: Efficient Hierarchical Reference and Quality Structure for Neural Video Coding
    Junqi Liao, Yaojun Wu, Chaoyi Lin, Zhipin Deng, Li Li, Dong Liu, Xiaoyan Sun.
    Proceedings of the 33rd ACM International Conference on Multimedia (ACM MM 2025).
@inproceedings{liao2025ehvc,
  title={EHVC: Efficient Hierarchical Reference and Quality Structure for Neural Video Coding},
  author={Liao, Junqi and Wu, Yaojun and Lin, Chaoyi and Deng, Zhipin and Li, Li and Liu, Dong and Sun, Xiaoyan},
  booktitle={Proceedings of the 33rd ACM International Conference on Multimedia},
  year={2025}
}

🙌 Acknowledgement

The intra model of this project is based on DCVC-DC.