In recent years, human pose estimation has greatly benefited from deep learning and huge gains in performance have been achieved on on the well-known FLIC, LSP, and MPII benchmarks. The trend to maximize the accuracy on benchmarks, however, resulted in computationally expensive deep network architectures that require expensive hardware and pre-training on large datasets. In this work, we propose an efficient deep network architecture that can be efficiently trained on mid-range GPUs without the need of any pre-training and that is on par with much more complex models on the benchmarks.
Our Qualitative Results on FLIC, LSP and MPII datasets.
If you use this code or pre-trained models for research purposes please cite the Paper
U. Rafi, I.Kostrikov, J. Gall, and B. Leibe, An Efficient Convolutional Network for Human Pose Estimation, in BMVC 2016.
Please send any questions or comments to Umer Rafi at email@example.com.