Perceiving Systems, Computer Vision

Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"

2019-09-11


We present the first method to perform automatic 3D pose, shape and texture capture of animals from images acquired in-the-wild. In particular, we focus on the problem of capturing 3D information about Grevy's zebras from a collection of images. We integrate the recent SMAL animal model into a network-based regression pipeline, which we train end-to-end on synthetically generated images with pose, shape, and background variation. We couple 3D pose and shape prediction with the task of texture synthesis, obtaining a full texture map of the animal from a single image. The predicted texture map allows a novel per-instance unsupervised optimization over the network features. We called the method SMALST (SMAL with learned Shape and Texture).

Author(s): Silvia Zuffi, Angjoo Kanazawa, Tanya Berger-Wolf, Michael J. Black
Department(s): Perceiving Systems
Research Projects(s): Animal Shape and Pose
Publication(s): {Three-D} Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"
Authors: Silvia Zuffi, Angjoo Kanazawa, Tanya Berger-Wolf, Michael J. Black
Release Date: 2019-09-11
License: The MIT License (MIT)
Copyright: Max Planck Society
Repository: https://github.com/silviazuffi/smalst