Abstract: A learning method of a machine learning system carries out the steps of: obtaining augmented reality images including a real image and at least one virtual element representative of the object and/or the characteristic region; obtaining, for each augmented reality image, learning information including, for at least one given virtual element of the augmented reality image: a model for segmenting the given virtual element, and a set of contour points corresponding to a parameterisation of the given virtual element; and learning on the basis of the plurality of augmented reality images and the learning information, delivering a set of parameters enabling the machine learning system to detect and model the object and/or the characteristic region in a given image.

Abstract: A method for generating a final image of an individual from an initial image of the individual acquired by a camera, the image being a still or contained in a video stream. The method includes detecting the face of the individual in the initial image, realistic positioning of a virtual frame on the face of the individual, generating an overlay that is superimposed on the initial image, the overlay comprising a projection of all or a portion of the virtual frame, generating the final image by merging the overlay with the initial image. The frame includes at least one ophthalmic lens characterized by an optical correction and/or an optical treatment. The method also includes, before the final step, a step of calculating the rendering of the ophthalmic lens according to the refraction of the ophthalmic lens and of a depth map of the initial image.

Abstract: A method for automatically determining at least one parameter associated with an ophthalmic device selected by an individual, said device comprising a frame referred to as selected frame, said determination being carried out from an acquired image of the face of the individual wearing the selected frame or a frame of a second ophthalmic device. The method includes the steps of: detecting at least one characteristic point of at least one eye of the individual the acquired image and estimating the three-dimensional position of the one or more characteristic point(s) detected; detecting the frame worn and estimating the three-dimensional position of the frame worn by aligning a three-dimensional representation of the frame worn with the frame worn in the acquired image; and determining the one or more parameters from the relative position of the eyes with respect to the three-dimensional representation of the selected frame.

Abstract: A method for generating a final image of an individual from an initial image of the individual acquired by a camera, the image being a still or contained in a video stream. The method includes detecting the face of the individual in the initial image, realistic positioning of a virtual frame on the face of the individual, generating an overlay that is superimposed on the initial image, the overlay comprising a projection of all or a portion of the virtual frame, generating the final image by merging the overlay with the initial image. The frame includes at least one ophthalmic lens characterized by an optical correction and/or an optical treatment. The method also includes, before the final step, a step of calculating the rendering of the ophthalmic lens according to the refraction of the ophthalmic lens and of a depth map of the initial image.

Abstract: A method for automatically determining at least one parameter associated with an ophthalmic device selected by an individual, said device comprising a frame referred to as selected frame, said determination being carried out from an acquired image of the face of the individual wearing the selected frame or a frame of a second ophthalmic device. The method includes the steps of: detecting at least one characteristic point of at least one eye of the individual the acquired image and estimating the three-dimensional position of the one or more characteristic point(s) detected; detecting the frame worn and estimating the three-dimensional position of the frame worn by aligning a three-dimensional representation of the frame worn with the frame worn in the acquired image; and determining the one or more parameters from the relative position of the eyes with respect to the three-dimensional representation of the selected frame.

Abstract: Disclosed is a method for determining at least one ocular measurement (pupillary distance, mono pupillary distance and/or heights) of a user, using a consumer-type digital image sensor. The method uses at least one image of the user's head, acquired by the image sensor and containing an object of known size. The calibration parameters of the camera are unknown or known with little precision.

Abstract: A method for determining ocular and optical measurements for the production and fitting of corrective eyeglasses for a user with the aid of the a camera. The method utilizes a protocol for reconstructing the system of the user's eyes in three dimensions by modeling the system of the eye, thereby providing precise ocular and optical measurements. The method uses test objects that are connected or not connected to the user's face.

Abstract: A method for generating a real-time realistic-looking image of a pair of virtual glasses positioned on a real user face image issued from a single image, a bundle of pictures, a video clip or a real-time camera streams. A face analysis element estimates the 3D rotation matrix, the 3D translation vector, morphology parameters of the user's face. A glasses positioning element associated with a try-on mode for look or real-size simulation estimates the 3D rotation matrix, the 3D translation vector, global and local deformation parameters of the virtual glasses, and arms articulation, adapted to the morphology parameters computed by the face analysis element. A realistic rendering element mixes the real user face image with the virtual glasses positioned by the glasses positioning element.

Abstract: A method for generating a final image from an initial image including an object suitable to be worn by an individual. The presence of the object in the initial image is detected. A first layer is superposed on the initial image. The first layer includes a mask at least partially covering the object in the initial image. The appearance of at least one part of the mask is modified. The suppression of all or part of an object in an image or a video is enabled. Also, a process of augmented reality intended to be used by an individual wearing a vision device on the face, and a try-on device for a virtual object.

Abstract: A method for generating a final image from an initial image including an object suitable to be worn by an individual. The presence of the object in the initial image is detected. A first layer is superposed on the initial image. The first layer includes a mask at least partially covering the object in the initial image. The appearance of at least one part of the mask is modified. The suppression of all or part of an object in an image or a video is enabled. Also, a process of augmented reality intended to be used by an individual wearing a vision device on the face, and a try-on device for a virtual object.

Abstract: A method of generating a digital model of a lens of a pair of glasses from images of the pair of glasses with an uniform background. The images being taken with a camera of an acquisition device. A silhouette of the lens is generated by clipping the lens in the taken images. A processor is configured to project the silhouette on a 3D surface of the digital model, adjust a surface of degree 2 to the projected silhouette, cut the adjusted surface according to the projected silhouette, extrude the adjusted surface from the 3D surface to obtain the desired thickness of the lens, and apply a realistic texture on the digital model of the lens. The texture depends of the angle of view of the lens.

Abstract: A method for estimating a person's interpupillary distance (PD). Data is acquired by utilizing a predefined movement of the person in front of a camera. A morphological and dimensional parameters are calculated based on the acquired data.

Abstract: A method and device for generating a simplified geometric model of a real pair of spectacles. The model includes a frame, lenses, and a predefined number of surfaces and normals thereof. An orientation of these normals is taken as an exterior of a convex envelop to the real pair of spectacles. The model is obtained in a phase. A set of shots of the real pair of spectacles to be modeled is produced with different angles-of-view and using different screen backgrounds with and without the real pair of spectacles. The simplified geometric model is constructed, consisting of a predefined number of surfaces and their normal beginning with a non-dense surface mesh and using an optimization algorithm that deforms the model's mesh so that the projections of its silhouette in each of the views best match the silhouettes detected in the images.

Abstract: A method of constructing images of a lens of a pair of glasses from an image of the pair of glasses with an uniform background. The image being taken with a numerical acquisition device. A silhouette of the lens is generated by clipping the lens in the taken image. A digital model of the lens is generated by a processor. The processor is configured to project the silhouette on a 3D surface of the digital model, adjust a surface of degree 2 to the projected silhouette, cut the adjusted surface according to the projected silhouette, extrude the adjusted surface from the 3D surface to obtain the desired thickness of the lens, and apply a realistic texture on the digital model of the lens. The texture depends of the angle of view of the lens.

Abstract: A method for generating a real-time realistic-looking image of a pair of virtual glasses positioned on a real user face image issued from a single image, a bundle of pictures, a video clip or a real-time camera streams. A face analysis element estimates the 3D rotation matrix, the 3D translation vector, morphology parameters of the user's face. A glasses positioning element associated with a try-on mode for look or real-size simulation estimates the 3D rotation matrix, the 3D translation vector, global and local deformation parameters of the virtual glasses, and arms articulation, adapted to the morphology parameters computed by the face analysis element. A realistic rendering element mixes the real user face image with the virtual glasses positioned by the glasses positioning element.

Abstract: A method and device for generating a simplified geometric model of a real pair of spectacles. The model includes a frame, lenses, and a predefined number of surfaces and normals thereof. An orientation of these normals is taken as an exterior of a convex envelop to the real pair of spectacles. The model is obtained in a phase. A set of shots of the real pair of spectacles to be modeled is produced with different angles-of-view and using different screen backgrounds with and without the real pair of spectacles. The simplified geometric model is constructed, consisting of a predefined number of surfaces and their normal beginning with a non-dense surface mesh and using an optimization algorithm that deforms the model's mesh so that the projections of its silhouette in each of the views best match the silhouettes detected in the images.

Abstract: Disclosed is a method for determining at least one ocular measurement (pupillary distance, mono pupillary distance and/or heights) of a user, using a consumer-type digital image sensor. The method uses at least one image of the user's head, acquired by the image sensor and containing an object of known size. The calibration parameters of the camera are unknown or known with little precision.

Abstract: A method for producing dynamic photorealistic 3D models for digitizing a three-dimensional object, that may include including transparent or reflective parts such as a pair of glasses, is adaptive for visualization and real time fitting, and includes movable fastening of the object to a support, pivoting about a vertical axis, placed opposite at least two vertically spaced image shooting devices, acquisition of object images by the image shooting devices during a rotation of the object about the vertical axis, and colorimetric correction of the acquired images.

Abstract: Method for creating a final real-time photorealistic image of a virtual object, corresponding to a real object arranged on an original photo of a user, in a realistic orientation related to the user's position, includes: detecting the presence of an area for the object in the photo; determining the position of characteristic points of the area for the object in the photo; determining the 3D orientation of the face, the angles ? and ? of the camera having taken the photo relative to the principal plane of the area; selecting the texture to be used for the virtual object, in accordance with the angle-of-view, and generating the view of the virtual object in 3D; creating a first layered rendering in the correct position consistent with the position of the placement area for the object in the original photo; obtaining the photorealistic rendering by adding overlays to obtain the final image.

Abstract: A method of detecting a predefined set of characteristic points of a face from an image of the face includes a step of making the shape and/or the texture of a hierarchy of statistical models of face parts converge over real data supplied by the image of the face.