Giang Bui

TL;DR: This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results and gauges the state-of-the-art in single imagesuper-resolution.

TL;DR: A multi-view recurrent neural network (MV-RNN) approach for 3D mesh segmentation that combines the convolutional neural networks and a two-layer long short term memory to yield coherent segmentation of 3D shapes is introduced.

TL;DR: The proposed novel deep learning-based approach that can generate high-resolution photo realistic point renderings from low-resolution point clouds using co-registered high-quality photographs as the ground truth data to train the deep neural network for point-based rendering outperforms state-of-the-art methods.

TL;DR: It is shown that incorporating contextual information can provide complimentary information for scale invariant feature transform and boost local keypoint matching performance, as well as be used to describe corner feature points.

TL;DR: This work demonstrates how to register a variety of 2D imagery with a range scan to construct photo-realistic models and to extract walking people captured in videos and model them in a 3D space.