Ultra High Fidelity Deep Image Decompression With l∞-Constrained Compression

We propose a novel asymmetric image compression system of light <inline-formula> <tex-math notation="LaTeX">$\ell _\infty $ </tex-math></inline-formula>-constrained predictive encoding and heavy-duty CNN-based soft decoding. The system achieves superior rate-distortion performances over the best of existing image compression methods, including BPG, WebP, FLIF and recent CNN codecs, in both <inline-formula> <tex-math notation="LaTeX">$\ell _{2}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$\ell _\infty $ </tex-math></inline-formula> error metrics, for bit rates near or above the threshold of perceptually transparent reconstruction. These remarkable coding gains are made by deep learning for compression artifact removal. A restoration CNN is designed to map a lossy compressed image to its original. Its unique strength is to enforce a tight error bound on a per pixel basis. As such, no small distinctive structures of the original image can be dropped or distorted, even if they are statistical outliers that are otherwise sacrificed by mainstream CNN restoration methods.