The concepts of risk aversion, chance-constrained optimization, and robust optimization
have developed significantly over the last decade. The statistical learning community has …

With the explosion in the number of digital images taken every day, the demand for more
accurate and visually pleasing images is increasing. However, the images captured by …

Recent works on plug-and-play image restoration have shown that a denoiser can implicitly
serve as the image prior for model-based methods to solve many inverse problems. Such a …

Abstract We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network
architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D …

Learning-based single image super-resolution (SISR) methods are continuously showing
superior effectiveness and efficiency over traditional model-based methods, largely due to …

Lead halide perovskite (LHP) semiconductors show exceptional optoelectronic properties.
Barriers for their applications, however, lie in their polymorphism, instability to polar solvents …

Signal processing, communications, and control have traditionally relied on classical
statistical modeling techniques. Such model-based methods utilize mathematical …

Compressive sensing (CS) is an effective technique for reconstructing image from a small
amount of sampled data. It has been widely applied in medical imaging, remote sensing …

Image denoising—removal of additive white Gaussian noise from an image—is one of the
oldest and most studied problems in image processing. Extensive work over several …

Many machine learning algorithms are vulnerable to almost imperceptible perturbations of
their inputs. So far it was unclear how much risk adversarial perturbations carry for the safety …