2020 · 39 citations · 12 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningData CompressionDeep LearningDigital Image ProcessingImage CompressionImage ProcessingLossy Data CompressionAutoencodersContext-based CompressionDeep Learning-based Image CompressionEntropy CodingEntropy EstimationEntropy In Data CompressionImage EncodingResolutions
In this paper, we present our image compression framework designed for CLIC 2020 competition. Our method is based on Variational AutoEncoder (VAE) architecture which is strengthened with residual structures. In short, we make three noteworthy improvements here. First, we propose a 3-D context entropy model which can take advantage of known latent representation in current spatial locations for better entropy estimation. Second, a light-weighted residual structure is adopted for feature learning during entropy estimation. Finally, an effective training strategy is introduced for practical adaptation with different resolutions. Experiment results indicate our image compression method achieves 0.9775 MS-SSIM on CLIC validation set and 0.9809 MS-SSIM on test set.
12
End-to-end Optimized Image Compression
Johannes Ballé, Valero Laparra, Eero P. Simoncelli · arXiv (Cornell University) · 2016 · 1K citations · Full text
Variational image compression with a scale hyperprior
David Minnen, Saurabh Singh, Sung Jin Hwang et al. · arXiv (Cornell University) · 2018 · 861 citations · Full text