3D Human Pose and Shape-aware Modelling

Sammanfattning: The focus of this thesis is the task of 3D pose estimation while taking into consideration the shape of a person in a single image. For rendering the human pose and the body shape we use a newly proposed statistical model, the SMPL [1]. We train a neural network to estimate the shape and the pose of a person in an image. Afterwards, we use an optimization procedure to further enhance the output. the network is trained by incorporating the optimized and the predicted parameters into the loss. This approach is based on SPIN [2]. We extend this method by using a stronger optimization that is based on several views and the error is summed over all of them. The main objective of this thesis is to utilize information from multiple views. The motivation for our method is to explore whether this optimization can provide better supervision to the network. In order to verify the effectiveness of our method, we conduct several experiments and we show appealing visual results. Lastly, to make the network generalize better we train simultaneously on seven datasets and achieve comparable to even better accuracy than similar methods from related work.