Rate-Distortion-Perception Theory for the Quadratic Wasserstein Space
By: Xiqiang Qu , Jun Chen , Lei Yu and more
Potential Business Impact:
Makes pictures clearer with less data.
We establish a single-letter characterization of the fundamental distortion-rate-perception tradeoff with limited common randomness under the squared error distortion measure and the squared Wasserstein-2 perception measure. Moreover, it is shown that this single-letter characterization can be explicitly evaluated for the Gaussian source. Various notions of universal representation are also clarified.
Similar Papers
A Theory of Universal Rate-Distortion-Classification Representations for Lossy Compression
Information Theory
Lets one AI learn many tasks at once.
Information-Theoretic Equivalences Across Rate-Distortion, Quantization, and Decoding
Information Theory
Makes data compression and error correction work together.
Universal Rate-Distortion-Classification Representations for Lossy Compression
Information Theory
Makes one computer brain learn many tasks.