Data Sets

This dataset contains a subset of the clouds used within the paper “Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks”. Each cloud is bundled as a volumetric density grid in Field3D and VDB format and comes with preview images and visualizations of cross-sections in 3 orthogonal directions.

Color and depth data of our modified Sponza scene, rendered using RenderMan. The dataset contains color and depth images from nine probes, six faces each, 600 frames each.

Machine learning Monte Carlo denoising dataset. The dataset contains pairs of noisy renderings and references rendered with many samples. The scenes are random perturbations of creative commons scenes rendered using the Tungsten renderer.

Test dataset from the paper Editable Parametric Dense Foliage from 3D Capture, ICCV 2017.

Here, we include all data for reproducing the experimental validation curves of Fig. 4a–d of the PLOS One article entitled “Quasistatic Cavity Resonance for Ubiquitous Wireless Power Transfer”. This data set includes measured, simulated, and analytically computed electric and magnetic fields, as well as all S-parameter data for reproducing the efficiency curves of panels d and e in Fig. 4 of the article.  We further include a Comsol Multiphysics (.mph file) model that can be used for reproducing simulations for the QSCR designed and tested in the article.

Tabulated database of shell-transport functions that quantify light transport in homogeneous media bounded by a spherical shell.

The provided dataset contains two scans of the right and left eyes of a person with blue eyes. One scan consists of an eyeball mesh, a sequence of iris meshes in different dilation states, iris and sclera textures, and a limbus opacity map. Also, a photo is included for reference.

The dataset contains 47 training sequences and 2 test sequences, encoded as tab-delimited text files. Columns 1-14 represent the feature elements at each time instant, and column 15 is the broadcast camera pan angle (in degrees).

The data set contains five different collections which include, beach vacations, Disney trips, London, Paris, and Washington DC. The set consists of a collection of five locations that include text files that contain links to Flickr images, album annotations and time ordering. There are no actual images on the set.