The Rate-Distortion-Perception Trade-Off with Algorithmic Realism
By: Yassine Hamdi, Aaron B. Wagner, Deniz Gündüz
Potential Business Impact:
Makes pictures look real when shrunk down.
Realism constraints (or constraints on perceptual quality) have received considerable recent attention within the context of lossy compression, particularly of images. Theoretical studies of lossy compression indicate that high-rate common randomness between the compressor and the decompressor is a valuable resource for achieving realism. On the other hand, the utility of significant amounts of common randomness has not been noted in practice. We offer an explanation for this discrepancy by considering a realism constraint that requires satisfying a universal critic that inspects realizations of individual compressed reconstructions, or batches thereof. We characterize the optimal rate-distortion trade-off under such a realism constraint, and show that it is asymptotically achievable without any common randomness, unless the batch size is impractically large.
Similar Papers
A Convergent Primal-Dual Algorithm for Computing Rate-Distortion-Perception Functions
Information Theory
Makes pictures smaller without losing important details.
Semantic Rate-Distortion Theory with Applications
Information Theory
Makes messages clearer and shorter for computers.
Computability of the Optimizer for Rate Distortion Functions
Information Theory
Makes data smaller, but finding the best way is hard.