The project aims at detailed and high quality 3D modelling of face shapes and expressions. The goal of MESH is to create and animate synthetic faces that are indistinguishable from real ones. Expressions will include speech and emotions. Complete heads will be modelled, including the hair, ears, etc, but also the neck and shoulders so that the integration with virtual bodies becomes possible. Also the synthesis of novel, but highly realistic virtual faces and caricatures will be supported. The work should lead to a complete modelling and animation suite.
Progress will be monitored continuously. The evolving tools will be used already during the project for real productions, as test and show cases. These span markets with different quality requirements, ranging from Internet communications, over TV productions, to movies
The goal of MESH is no less than creating virtual heads that are indistinguishable from real ones in terms of their shape, texture, and dynamics (emotions and speech). Even for caricatures such properties ought to be convincing. We'll learn from exemplars. Bringing to bear the latest in 3D acquisition, the project will capture detailed 3D dynamics of faces.
Learned motions together with guidance by a "face space" will allow us to animate models of existing and novel faces. Moreover, faces will not be handled in isolation but modelling will target complete heads, i.e. including ears, hair, eyes, teeth, tongue, neck and shoulders. MESH counts several companies among its contractors. They have direct plans for exploitation, both for production tools to be marketed and as tools to be used in productions of their own (for TV, internet and movies). Strengthening our partners' position in these markets is a key objective.
The work is structured in the following workpackages. WP1 corresponds to the management of the project. WP2 is concerned with user requirements and the gathering of test data. The latter will include data to be used for the modelling of both static faces and facial and head dynamics. WP3 fixes the system specifications, in view of the requirements of different markets, but mostly with an emphasis on high levels of realism. WP4 deals with the actual system development and integration, leading to animation suites for complete heads.
Both speech and emotional expressions will be considered. Complete heads will be considered, including hair, neck and shoulders. WP5 validates the results. Part of that validation will be through the realisation of show case productions. WP6 assesses and evaluates the results, based on users' reactions to the show case productions. WP7 handles the dissemination of the results and the exploitation planning, taking into account the market and competing technology.
The different WPs come with detailed milestones and deliverables. Here the general evolution of the work is sketched. After year 1 specs will be available for the different markets and most of the static head design and modelling work will be finished.
After year 2, head dynamics will have been analysed and initial animations have started. After year 2 1/2, the tools will have been integrated and used for test case productions.
Synthesis, Producing Characterizations of high-purity cyclic phosphonitryl Cl trimer and related poly(bis trifluoroalkoxy) phosphazene (PTFEP), tailored block-urea-polydimethyl-siloxane (BPDMS), 1-(trimethylsilyl)-1-propyne and PTMSP polymers from Nb and Ta catalysts.Permeation properties of PTFEP, BPDMS, PTMSP with H2O, DMK, toluene and dichloromethane: isothermal sorption and vapour permeation studies for binary systems (20-50°C); gas permeability of N2 and O2; permeation of ternary systems for PTFEP and BPDMS; activity and temperature effects. Polymer performances: PTMSP: selective, highly permeable (Tol., DiCl), very good films; BPDMS: high selectivity, good permeability (Tol, DiCl), good films; PTFEP high selectivity for DMK, medium-low permeability, excellent films. Preparation of disk-type membrane module based on PTMSP (8-10µm) (membrane area of 0.75 m2)having high steady permeances. Operation of a hybrid system for Tol. and DiCl removal from contaminated water
Funding SchemeCSC - Cost-sharing contracts
1211 Geneve 4