Rohit Pandey

TL;DR: Multiple experiments, comparisons, and applications show that The Relightables significantly improves upon the level of realism in placing volumetrically captured human performances into arbitrary CG scenes.

TL;DR: To enhance methane production in situ in bituminous coal seams, distribution of microorganisms in the formation water collected from a coalbed methane well was investigated and revealed the presence of 185 bacteria species and nine archaea species which were dramatically different from those in the original formation water.

TL;DR: In this paper, a laboratory-scale coal permeability measurement study using the pressure pulse decay method was carried out to establish the permeability variation trend impacted by the combined effects of effective stresses and coal matrix shrinkage associated with gas depletion under uniaxial strain condition for San Juan basin coal.

TL;DR: A novel technique to relight images of human faces by learning a model of facial reflectance from a database of 4D reflectance field data of several subjects in a variety of expressions and viewpoints is presented.

TL;DR: In this paper, the authors apply traditional 3D reconstruction to register the photos and approximate the scene as a point cloud, and train a neural network to learn the mapping of these initial renderings to the actual photos.