Ecole Polytechnique Federale De Lausanne

Sami Arpa

Sabine Süsstrunk

Roger David Hersch

Gabriel Autès

A method of classifying a media includes receiving a media file and extracting therefrom first and second data streams including first and second media content, respectively, the media content being associated with the media item. First and second feature vectors describing the first and second media content, respectively, are generated. At least a first single feature vector representing the first sequence of first feature vectors and the second sequence of second feature vectors is generated, or at least a first single feature vector representing at least the first sequence of first feature vectors is generated. A second feature vector representing at least the second sequence of second feature vectors is generated. A probability vector from the first single feature vector, or from the first and second single feature vectors is generated. A user profile suitability class is assigned to the media item based on the probability vector.

Dynamic media content categorization method

We disclose a method for synthesizing by computer an artwork where 2D and 3D contents are integrated within a same composition. Such an artwork creates plausible effects for the viewers by showing a different relationship between 2D and 3D at each viewing angle. Methods are proposed for ensuring the continuity between the 2D and the 3D parts in terms of mesh geometry and reflected colors. The user selects from a given scene a region of interest (ROI) to be reproduced in 3D. A flat rendering grid is created that matches the topology and tesselation of the ROI. The ROI is attached to the rendering grid. To enhance the continuity between the 2D and the 3D parts of a scene object, the 2D part of the object can be represented as bas-relief. Designers can create 2D-3D sculpture paintings for decoration, exhibitions, and homes.

Growing community of inventors

Lausanne, Switzerland

Sami Arpa