Unsupervised learning of object frames by dense equivariant image labelling
This addresses the challenge of unsupervised 3D object modeling for computer vision, with applications to articulated and deformable objects like human faces.
The paper tackles the problem of extracting dense object-centric coordinate frames from images without supervision, achieving invariance to deformations and providing a neural network that maps pixels to object coordinates.
One of the key challenges of visual perception is to extract abstract models of 3D objects and object categories from visual measurements, which are affected by complex nuisance factors such as viewpoint, occlusion, motion, and deformations. Starting from the recent idea of viewpoint factorization, we propose a new approach that, given a large number of images of an object and no other supervision, can extract a dense object-centric coordinate frame. This coordinate frame is invariant to deformations of the images and comes with a dense equivariant labelling neural network that can map image pixels to their corresponding object coordinates. We demonstrate the applicability of this method to simple articulated objects and deformable objects such as human faces, learning embeddings from random synthetic transformations or optical flow correspondences, all without any manual supervision.