Autoencoder Based Image Compression: Can the Learning be Quantization Independent?
By Thierry Dumas, Aline Roumy, Christine M. Guillemot. 2018
59 citations recorded by the source corpus.
This paper explores the problem of learning transforms for image compression via autoencoders. Usually, the ratedistortion performances of image compression are tuned by varying the quantization step size. In the case of autoen-coders, this in principle would require learning one transform per rate-distortion point at a given quantization step size. Here, we show that comparable performances can be obtained with a unique learned transform. The different rate-distortion points are then reached by varying the quantization step size at test time. This approach saves a lot of training time.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Trevor Darrell
- Dacheng Tao
- Jitendra Malik
- Xiaogang Wang
- Li Fei-Fei
- Ming-Hsuan Yang
- Andrew Zisserman
Citations in the corpus
- Learned Video Compression (2018, background): “In the last two years, we have seen a great surge of ML-based image compression approaches [13, 39, 40, 5, 4, 12, 20, 38, 33, 18, 2, 22, 6, 3, 8, 27, 28].”
- CompressAI: a PyTorch library and evaluation platform for end-to-end compression research (2020, unknown): “Minimizing the bit-stream size requires to learn shared probability models between the encoder and decoder (priors) [1, 13, 2], as well as using relaxation methods [14, 15, 13, 16] to approximate the non-differentiable quantization of the latent values.”