Deep contextual video compression
Most of the existing neural video compression methods adopt the predictive coding
framework, which first generates the predicted frame and then encodes its residue with the …
framework, which first generates the predicted frame and then encodes its residue with the …
Scale-space flow for end-to-end optimized video compression
Despite considerable progress on end-to-end optimized deep networks for image
compression, video coding remains a challenging task. Recently proposed methods for …
compression, video coding remains a challenging task. Recently proposed methods for …
Temporal context mining for learned video compression
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 …
few years. In this work, we address end-to-end learned video compression with a special …
Videofactory: Swap attention in spatiotemporal diffusions for text-to-video generation
We present VideoFactory, an innovative framework for generating high-quality open-domain
videos. VideoFactory excels in producing high-definition (1376$\times $768), widescreen …
videos. VideoFactory excels in producing high-definition (1376$\times $768), widescreen …
Video compression with rate-distortion autoencoders
A Habibian, T Rozendaal… - Proceedings of the …, 2019 - openaccess.thecvf.com
In this paper we present aa deep generative model for lossy video compression. We employ
a model that consists of a 3D autoencoder with a discrete latent space and an …
a model that consists of a 3D autoencoder with a discrete latent space and an …
Implicit neural video compression
We propose a method to compress full-resolution video sequences with implicit neural
representations. Each frame is represented as a neural network that maps coordinate …
representations. Each frame is represented as a neural network that maps coordinate …
Motion information propagation for neural video compression
In most existing neural video codecs, the information flow therein is uni-directional, where
only motion coding provides motion vectors for frame coding. In this paper, we argue that …
only motion coding provides motion vectors for frame coding. In this paper, we argue that …
Learned video compression with efficient temporal context learning
In contrast to image compression, the key of video compression is to efficiently exploit the
temporal context for reducing the inter-frame redundancy. Existing learned video …
temporal context for reducing the inter-frame redundancy. Existing learned video …
End-to-end neural video coding using a compound spatiotemporal representation
Recent years have witnessed rapid advances in learnt video coding. Most algorithms have
solely relied on the vector-based motion representation and resampling (eg, optical flow …
solely relied on the vector-based motion representation and resampling (eg, optical flow …
Instance-adaptive video compression: Improving neural codecs by training on the test set
T Van Rozendaal, J Brehmer, Y Zhang… - arXiv preprint arXiv …, 2021 - arxiv.org
We introduce a video compression algorithm based on instance-adaptive learning. On each
video sequence to be transmitted, we finetune a pretrained compression model. The optimal …
video sequence to be transmitted, we finetune a pretrained compression model. The optimal …