👨 Code for "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression"

Arbitrary object tracking at 50-100 FPS with Fully Convolutional Siamese networks.

Code for NeurIPS 2018: Cooperative Holisctic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation

Implements the work done by F. Landis Merkley to calculate the average quaternion.

A foveated object detector that uses the Freeman-Simoncelli model as its visual field, HoG features and a mixture of linear classifiers