MobileCodec: Neural Inter-frame Video Compression on Mobile Devices

Hoang Le, Liang Zhang, Amir Said, Guillaume Sautiere, Yang Yang +4 more
7/18/2022
cs.CVcs.MMeess.IV

No confident code implementation found for this paper.

Abstract

Realizing the potential of neural video codecs on mobile devices is a big technological challenge due to the computational complexity of deep networks and the power-constrained mobile hardware. We demonstrate practical feasibility by leveraging Qualcomm's technology and innovation, bridging the gap from neural network-based codec simulations running on wall-powered workstations, to real-time operation on a mobile device powered by Snapdragon technology. We show the first-ever inter-frame neural video decoder running on a commercial mobile phone, decoding high-definition videos in real-time while maintaining a low bitrate and high visual quality.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Device

89% match2023

Towards Practical Real-Time Neural Video Compression

86% match1 repo7732025

Towards Real-Time Neural Video Codec for Cross-Platform Application Using Calibration Information

86% match2023

DCVC-MB: Neural B-Frame Video Compression using State Space Models

85% match2026

LSCD: A Large-Scale Screen Content Dataset for Video Compression

84% match2023

Ristretto: Hardware-Oriented Approximation of Convolutional Neural Networks

84% match1 repo2.2k2016

Cite this paper

@article{le2022mobilecodec,
  title  = {MobileCodec: Neural Inter-frame Video Compression on Mobile Devices},
  author = {Hoang Le and Liang Zhang and Amir Said and Guillaume Sautiere and Yang Yang and Pranav Shrestha and Fei Yin and Reza Pourreza and Auke Wiggers},
  year   = {2022},
  eprint = {2207.08338},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.08338v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.08338.svg)](https://codeofpaper.com/paper/2207.08338)

Discussion