Uncertainty Estimation Optimization for Reliable Remote Sensing Single-Image Super-Resolution (opens in new tab)

Remote sensing (RS) single-image super-resolution (SISR) is a classic ill-posed problem in low-level vision, characterized by a one-to-many mapping. This ill-posedness can lead to aleatoric uncertainty, thereby rendering the reconstruction results unreliable. Given that RS images typically carry strict physical significance, quantifying uncertainty to evaluate pixel-wise reliability in RSSISR results is of critical importance. In this article, we estimate image uncertainty based on differenti...