Syed Waqas Zamir

TL;DR: MPRNet as discussed by the authors proposes a multi-stage architecture that progressively learns restoration functions for the degraded inputs, thereby breaking down the overall recovery process into more manageable steps, and introduces a novel per-pixel adaptive design that leverages in-situ supervised attention to reweight the local features.

TL;DR: MIRNet as mentioned in this paper proposes a multi-scale residual block containing several key elements: (a) parallel multi-resolution convolution streams for extracting mult-scale features, (b) information exchange across the multiresolution streams, (c) spatial and channel attention mechanisms for capturing contextual information, and (d) attention-based multiscale feature aggregation.

TL;DR: CycleISP as discussed by the authors is a framework that models camera imaging pipeline in forward and reverse directions, which allows to produce any number of realistic image pairs for denoising both in RAW and sRGB spaces.

TL;DR: This paper demonstrates that the Bayesian uncertainty estimates directly correlate with the rarity of classes and the difficulty level of individual samples, and presents a novel framework for uncertainty based class imbalance learning that efficiently utilizes sample and class uncertainty information to learn robust features and more generalizable classifiers.

TL;DR: Transformer networks as mentioned in this paper enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks e.g., Long short-term memory (LSTM).