ShinySMVS: a dataset for multi-view stereopsis training and reconstruction applications

A large collection of synthetic, path-traced renderings for use in multi-view stereopsis and 3D reconstruction applications. The material properties are primarily non-Lambertian (reflective metals). Ground truth depth maps, model geometry, object masks and camera extrinsic and intrinsic data is provided together with the rendered images. A total of 18,000 samples are provided (45 camera views for 400 scenes), varying the illumination using five, high-definition HDR environemnt textures, four models (teapot, bunny, armadillo and dragon), ten material properties (bricks, brushed metal, ceramic, checkerboard, concrete, copper, grunge metal, marble, piano/ivory, and steel) and two camera forcal lengths (35 mm and 50 mm). File descriptions: + ShinySMVS_sample.jpg - a visual collage of 8 scenes, illustrating the variability introduced by using different models, illumination, material properties and camera focal lengths. + sample_armadillo1bricks50mm.zip - A single ShinySMVS scene sample for easy viewing and download (31Mb). + ShinySMVS_576p.tar.xz - The full ShinySMVS dataset containing all 400 scenes (768x576 pixel resolution). Note that tar.xz archive used due to file size limitations (8.6Gb). + PFMdemo.zip - Python example source code for loading ground truth depth map (PFM file format) as a numpy array. + modelSTL - Stereolithography (STL) file for the models used in the dataset.