MIPT, Moscow, Russia
In XXI International Conference on Neuroinformatics, October 7-11, 2019, Dolgoprudny, Moscow region, Russia
Examples of our image-to-voxel translation based on generative adversarial network and frustum voxel model. Input color image (left). Ground truth frustum voxel model slices colored as a depth map (middle). The voxel model output (right).
Reconstruction of a 3D model from a single image is challenging. Nevertheless, recent advances in deep learning methods demonstrated exciting progress toward single-view 3D object reconstruction. However, successful training of a deep learning model requires an extensive dataset with pairs of geometrically aligned 3D models and color images. While manual dataset collection using photogrammetry of laser scanning is challenging, the 3D modeling provides a promising method for data generation. Still, a deep model should be able to generalize from synthetic to real data.
SyntheticVoxels Dataset poster.
Our VoxelCity dataset includes 3D models of 21 scenes, 18,836 color images with ground-truth 3D models, depth maps and 6D poses of seven object classes: human, car, bicycle, truck, van.
For download "SyntheticVoxels Dataset" dataset write to vl.kniaz@gosniias.ru
Created date: 2022-10-13 10:04:28
Last update: 2022-10-13 10:04:28