Neural video compression with diverse contexts

J Li, B Li, Y Lu - Proceedings of the IEEE/CVF conference …, 2023‏ - openaccess.thecvf.com
For any video codecs, the coding efficiency highly relies on whether the current signal to be
encoded can find the relevant contexts from the previous reconstructed signals. Traditional …

Neural video compression with feature modulation

J Li, B Li, Y Lu - Proceedings of the IEEE/CVF Conference …, 2024‏ - openaccess.thecvf.com
The emerging conditional coding-based neural video codec (NVC) shows superiority over
commonly-used residual coding-based codec and the latest NVC already claims to …

Hybrid spatial-temporal entropy modelling for neural video compression

J Li, B Li, Y Lu - Proceedings of the 30th ACM International Conference …, 2022‏ - dl.acm.org
For neural video codec, it is critical, yet challenging, to design an efficient entropy model
which can accurately predict the probability distribution of the quantized latent …

Temporal context mining for learned video compression

X Sheng, J Li, B Li, L Li, D Liu… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Applying deep learning to video compression has attracted increasing attention in recent
few years. In this work, we address end-to-end learned video compression with a special …

Coarse-to-fine deep video coding with hyperprior-guided mode prediction

Z Hu, G Lu, J Guo, S Liu, W Jiang… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
The previous deep video compression approaches only use the single scale motion
compensation strategy and rarely adopt the mode prediction technique from the traditional …

Transformer-based transform coding

Y Zhu, Y Yang, T Cohen - International conference on learning …, 2022‏ - openreview.net
Neural data compression based on nonlinear transform coding has made great progress
over the last few years, mainly due to improvements in prior models, quantization methods …

Hnerv: A hybrid neural representation for videos

H Chen, M Gwilliam, SN Lim… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Implicit neural representations store videos as neural networks and have performed well for
vision tasks such as video compression and denoising. With frame index and/or positional …

VCT: A video compression transformer

F Mentzer, G Toderici, D Minnen, SJ Hwang… - arxiv preprint arxiv …, 2022‏ - arxiv.org
We show how transformers can be used to vastly simplify neural video compression.
Previous methods have been relying on an increasing number of architectural biases and …

C3: High-performance and low-complexity neural compression from a single image or video

H Kim, M Bauer, L Theis… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Most neural compression models are trained on large datasets of images or videos in order
to generalize to unseen data. Such generalization typically requires large and expressive …

Dnerv: Modeling inherent dynamics via difference neural representation for videos

Q Zhao, MS Asif, Z Ma - … of the IEEE/CVF Conference on …, 2023‏ - openaccess.thecvf.com
Existing implicit neural representation (INR) methods do not fully exploit spatiotemporal
redundancies in videos. Index-based INRs ignore the content-specific spatial features and …