Subeesh Vasu

TL;DR: This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones and proposes solutions that significantly improved baseline results defining the state-of-the-art for image enhancement on smartphones.

TL;DR: In this paper, the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones was presented, where participants were solving the classical image super-resolution problem with a bicubic downscaling factor of 4.

TL;DR: A convolutional neural network-based approach to handle kernel uncertainty in non-blind motion deblurring, which provides multiple latent image estimates corresponding to different prior strengths obtained from a given blurry observation in order to exploit the complementarity of these inputs for improved learning.

TL;DR: The proposed network, called enhanced perceptual super-resolution network (EPSR), is trained with a combination of mean squared error loss, perceptual loss, and adversarial loss and achieves the state-of-the-art trade-off between distortion and perceptual quality while the existing methods perform well in either of these measures alone.

TL;DR: A first-of-its-kind pipeline to recover the latent image of a 3D scene from a set of such RS distorted images by sequentially recovering both the camera motion and scene structure while accounting for RS and occlusion effects is developed.