CompressAI: a PyTorch library and evaluation platform for end-to-end compression research
By Jean Bégaint, Fabien Racap'e, Simon Feltman, Akshay Pushparaja. arXiv.org, 2020
569 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
View Paper: https://www.semanticscholar.org/paper/19867d7dd59eaaef53f61d68ff6380209a63e9f5
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yee Whye Teh
- Chris J. Maddison
- Arnaud Doucet
- Ruslan Salakhutdinov
- Benjamin Bloem-Reddy
- Jiahao Li
- Yan Lu
- Bin Li
In Computer Vision and Pattern Recognition
- Yan Lu
- Bin Li
- Jiahao Li
- Benjamin Bloem-Reddy
- Arnaud Doucet
- Yee Whye Teh
- Milad Alizadeh
- Chris J. Maddison
In Signal Processing
- Benjamin Bloem-Reddy
- Arnaud Doucet
- Yee Whye Teh
- Jiahao Li
- Yan Lu
- Bin Li
- Chris J. Maddison
- Emilien Dupont
Citations in the corpus
- Deep Contextual Video Compression (2021, methodology): “As this paper only focuses on inter frame coding, for intra frame coding, we directly use existing deep image compression models provided by CompressAI [36].”
- Lossy Compression for Lossless Prediction (2021, background): “’s [134] implementation which is a Pytorch re-implementation of [28].”
- COIN: COmpression with Implicit Neural representations (2021, methodology): “To benchmark our model, we use the CompressAI library [4] and the pre-trained models provided therein.”