HANeRV: Hierarchically Adaptive Neural Representation for Video Compression
- 29 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 5773-5788
Abstract
Recent advances in video compression introduce implicit neural representation (INR) based methods, which effectively capture global dependencies and characteristics of entire video sequences. Unlike traditional and deep learning based approaches, INR-based methods optimize network parameters from a global perspective, resulting in superior compression potential. However, most current INR methods utilize a fixed and uniform network architecture across all frames, limiting their adaptability to dynamic variations within and between video sequences. This often leads to suboptimal compression outcomes as these methods struggle to capture the distinct nuances and transitions in video content. To overcome these challenges, we propose Hierarchically Adaptive Neural Representation for Video Compression (HANeRV), an innovative INR-based video compression network that adaptively conducts structure optimisation based on the specific content of each video sequence. To better capture dynamic information across video sequences, we propose a dynamic architecture-level adjustment (DAA). Furthermore, to enhance the capture of dynamics between frames within a sequence, we implement a dynamic frame-level adjustment (DFA). Finally, to effectively capture spatial structural information within video frames, thereby enhancing the detail restoration capabilities of HANeRV, we devise a structure level hierarchical structural adaptation (HSA). Experimental results show that HANeRV achieves state-of-the-art performance among INR-based video compression methods and surpasses the H.266/VVC (x266, medium preset) anchor on diverse datasets.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62461160310)
- National Natural Science Foundation of China (62521007)
- National Natural Science Foundation of China (62431011)
- Fundamental Research Funds for the Central Universities (E2ET1104)
This publication has 83 references indexed in Scilit:
- SNeRV: Spectra-Preserving Neural Representation for Video2024
- Fast Encoding and Decoding for Implicit Video Representation2024
- E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context2022
- Implicit Neural Representations for Image Compression2022
- CANF-VC: Conditional Augmented Normalizing Flows for Video Compression2022
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation2019
- Deep Kalman Filtering Network for Video Compression Artifact Reduction2018
- Video Compression Through Image Interpolation2018
- Conditional Probability Models for Deep Image Compression2018
- Multi-frame Quality Enhancement for Compressed Video2018