In this work, we propose a method for solving batch denoising using the Blahut-Arimoto algorithm (BA). Theoretical results show that our denoising estimation is highly likely to be close to the best result.

Rate-distortion theory provides a framework for understanding the limits of source coding. Energy-based models (EBMs), which have a broad range of applications in fields such as physics, statistics, and machine learning, can be used to estimate these limits. In this work, we demonstrate how EBMs can be used to estimate rate-distortion functions, and show that our empirical estimates agree with known closed-form expressions and bounds.