Integrating Adaptive Sampling for Optimal Learned Video Compression

Wuyang Cong, Yuzhuo Kong, Ming Lu, Lizhong Wang, Weijing Shi, Zhan Ma

Abstract

We propose a novel adaptive prediction network that dynamically determines the optimal sampling factor and Lagrangian multiplier for encoding each frame, guided by sequential information. By exploiting spatio-temporal redundancy through adaptive sampling, our method reduces bitrate consumption while preserving the reconstruction quality with adjusted rate-distortion coefficients. Experimental results demonstrate significant performance gains over representative learned video compression models across various datasets, with reduced encoding and decoding latency.
BibTeX
@inproceedings{cong2025integrating,
  author = {Wuyang Cong and Yuzhuo Kong and Ming Lu and Lizhong Wang and Weijing Shi and Zhan Ma},
  title = {{Integrating Adaptive Sampling for Optimal Learned Video Compression}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2025},
  doi = {10.1109/icassp49660.2025.10888457},
}

Loading related content...

Figure