CompressAI: a PyTorch library and evaluation platform for end-to-end compression research

11/05/2020
by   Jean Bégaint, et al.
0

This paper presents CompressAI, a platform that provides custom operations, layers, models and tools to research, develop and evaluate end-to-end image and video compression codecs. In particular, CompressAI includes pre-trained models and evaluation tools to compare learned methods with traditional codecs. Multiple models from the state-of-the-art on learned end-to-end compression have thus been reimplemented in PyTorch and trained from scratch. We also report objective comparison results using PSNR and MS-SSIM metrics vs. bit-rate, using the Kodak image dataset as test set. Although this framework currently implements models for still-picture compression, it is intended to be soon extended to the video compression domain.

READ FULL TEXT

page 16

page 17

page 18

research
06/29/2020

OpenDVC: An Open Source Implementation of the DVC Video Compression Method

We introduce an open source Tensorflow implementation of the Deep Video ...
research
01/05/2022

Learning True Rate-Distortion-Optimization for End-To-End Image Compression

Even though rate-distortion optimization is a crucial part of traditiona...
research
04/18/2018

Video Compression through Image Interpolation

An ever increasing amount of our digital communication, media consumptio...
research
04/16/2018

M-PACT: Michigan Platform for Activity Classification in Tensorflow

Action classification is a widely known and popular task that offers an ...
research
06/28/2023

Multi-Scale Deformable Alignment and Content-Adaptive Inference for Flexible-Rate Bi-Directional Video Compression

The lack of ability to adapt the motion compensation model to video cont...
research
04/09/2020

Feedback Recurrent Autoencoder for Video Compression

Recent advances in deep generative modeling have enabled efficient model...
research
03/06/2021

End-to-end optimized image compression for multiple machine tasks

An increasing share of captured images and videos are transmitted for st...

Please sign up or login with your details

Forgot password? Click here to reset