487 papers with code • 0 benchmarks • 19 datasets
Super resolution is the task of taking an input of a low resolution (LR) and upscaling it to that of a high resolution.
( Credit: MemNet )
Such methods, however, cannot guarantee that the input measurements are satisfied in the recovered image, since the learned parameters by the network are applied to every test image.
Then, a task transformer module is designed to embed and synthesize the relevance between the two tasks.
In this paper, we propose a novel reference based image super-resolution approach via Variational AutoEncoder (RefVAE).
Although SRFlow tried to account for ill-posed nature of the super-resolution by predicting multiple high-resolution images given a low-resolution image, there is room to improve the diversity and visual quality.
Therefore, high-quality correspondence matching is critical.
However, performing local transfer is difficult because of two gaps between input and reference images: the transformation gap (e. g. scale and rotation) and the resolution gap (e. g. HR and LR).
Spine-related diseases have high morbidity and cause a huge burden of social cost.
In this work we introduce a novel stochastic algorithm dubbed SNIPS, which draws samples from the posterior distribution of any linear inverse problem, where the observation is assumed to be contaminated by additive white Gaussian noise.