Descripció del projecte
Recent learning approaches that implicitly represent surface geometry using neural representations have shown impressive results in the problem of multiview 3D reconstruction. The effectiveness of these techniques is, however, subject to a large number (several tens) of input views of the scene and computationally demanding optimizations. This prevents them from being applicable on large volumes of data available in tech companies.
In this thesis, we will focus on the problem of full head 3D reconstruction from a few input images using implicit representations. We will research different approaches to alleviate the computational cost without hampering the accuracy of the recovered geometry. In particular, we will take advantage of the capacity of Crisalix company to capture and annotate vast amounts of full head 3D scans, to build strong priors. These priors will then be integrated within the estimation process, to provide accurate 3D head reconstructions from very few (and eventually one) images.
The outcome of this thesis will be integrated in the company product, an intelligent tool to assist professionals in plastic and cosmetic surgery, but it can also be applied to other related-applications, like in the development of avatars or online retailing apparel industry.
The project will be carried in cooperation with the following:
• Crisalix, in Barcelona.
• Institut de Robòtica i Informàtica Industrial in the Universitat Politècnica de Catalunya.
The scientific advisor at IRI will be Dr. Francesc Moreno Noguer.
The responsible for part of the company will be Dr. Gil Triginer.
