Forwarding you to www.robots.ox.ac.uk

Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild - Visual Geometry Group blog unsplash-logo

Summary: We propose a method to learn weakly symmetric deformable 3D object categories from raw single-view images, without ground-truth 3D, multiple views, 2D/3D keypoints, prior shape models or any other supervision.