Joint Autoregressive and Hierarchical Priors for Learned Image Compression

David Minnen, Johannes Ballé, George D. Toderici

Neural Information Processing Systems 

Most recent methods for learning-based, lossy image compression adopt an approach based on transform coding [1]. In this approach, image compression is achieved by first mapping pixel data into a quantized latent representation and then losslessly compressing the latents.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found