Model distortions in Bayesian MAP reconstruction

53 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The Perception-Distortion Tradeoff (2017, background): “This behavior has also be studied in [29].”
Learning Graphical Model Parameters with Approximate Marginal Inference (2013, background): “Here, ψ ( x c , y ) indicates that the value for a particular conﬁguration x c depends on the input y .”
Gaussian sampling by local perturbations (2010, background): “Motivated by [14, 23], we show here how this can lead to a novel Bayesian treatment of signal restoration under a total variation (TV) prior P (x) ∝ ∏N−1 l=1 L(∆xl;α), which imposes an L1 penalty on the signal diferrences ∆xl = xl − xl+1.”
A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them (2013, background): “Another reason might be that the MAP estimator actually favors the “wrong” penalty functions (Nikolova 2007; Schmidt et al. 2010).”