Tomasz Niewiadomski, Anastasios Yiannakidis, Hanz Cuevas-Velasquez, Soubhik Sanyal
Michael J. Black, Silvia Zuffi, Peter Kulits
Data and code coming soon.
We propose a pipeline for the scalable generation of realistic 3D animal pose and shape estimation training data. Training solely on data produced using our pipeline, we achieve state-of-the-art performance on a real-world 3D pose and shape estimation benchmark.