Estimating 3D shape from monocular 2D images is a challenging and ill-posed problem. Some of these challenges can be alleviated if 3D shape priors are taken into account. In the field of human body shape estimation, research has shown that accurate 3D body estimations can be achieved through optimization, by minimizing error functions on image cues, such as e.g. the silhouette. These methods though, tend to be slow and typically require manual interactions (e.g. for pose estimation). In this talk, we present some recent works that try to overcome such limitations, achieving interactive rates, by learning mappings from 2D image to 3D shape spaces, utilizing data-driven priors, generated from statistically learned parametric shape models. We demonstrate this, either by extracting handcrafted features or directly utilizing CNN-s. Furthermore, we introduce the notion and application of cross-modal or multi-view learning, where abundance of data coming from various views representing the same object at training time, can be leveraged in a semi-supervised setting to boost estimations at test time. Additionally, we show similar applications of the above techniques for the task of 3D garment estimation from a single image.
Biography: Endri Dibra is a PhD student at the Computer Graphics Lab of ETH Zurich, under the supervision of Prof. Markus Gross. He received his B.Sc. degree in Electrical Engineering and Computer Science from Jacobs University Bremen and his M.Sc. degree in Robotics, Systems and Control from ETH Zurich. His research is focused on 3D shape estimation from monocular images via learning. His research interests in broad span from autonomous robot control to deep learning and free view-point video.