Abstract

International audience; The rise of virtual and augmented reality fuels an increased need for contents suitable to these new technologies including 3D contents obtained from real scenes. We consider in this paper the problem of 3D shape reconstruction from multi-view RGB images. We investigate the ability of learning-based strategies to effectively benefit the reconstruction of arbitrary shapes with improved precision and robustness. We especially target real life performance capture, containing complex surface details that are difficult to recover with existing approaches. A key step in the multi-view reconstruction pipeline lies in the search for matching features between viewpoints in order to infer depth information. We propose to cast the matching on a 3D receptive field along viewing lines and to learn a multi-view photoconsistency measure for that purpose. The intuition is that deep networks have the ability to learn local photometric configurations in a broad way, even with respect to different orientations along various viewing lines of the same surface point. Our results demonstrate this ability, showing that a CNN, trained on a standard static dataset, can help recover surface details on dynamic scenes that are not perceived by traditional 2D feature based methods. Our evaluation also shows that our solution compares on par to state of the art reconstruction pipelines on standard evaluation datasets, while yielding significantly better results and generalization with realistic performance capture data. Document type: Part of book or chapter of book

Abstract

Open Distributed Processing (ODP) is a framework for specifying open distributed systems, under development by the International Standards Organisation (ISO). It is based on the general idea of viewpoints - i.e. partial specifications of an overall system, from different perspectives - but assumes five specific, named viewpoints, which are described informally in the ODP Reference Model (RM-ODP). This paper summarises some observations regarding an attempt to use ODP to specify a complex air traffic control system. Some of the key issues that arise are discussed further in the context of the formal specification of a simpler, idealised model, involving two formalised viewpoints - the Information Viewpoint (a high-level, abstract specification, in Z), and the Computational Viewpoint (a specification of distributed components and objects, in Object-Z). Document type: Book