Abstract: A method and device are provided for rendering an image. The method comprises receiving an image from at least two different camera positions and determining a camera orientation and at least one image attribute associated with each of the positions. A model is then generated of the image based on the attribute and camera orientation associated with the received camera positions of the image. The model is enabled to provide a virtual rendering of the image at a plurality viewing orientations and selectively providing appropriate attributes associated with the viewing orientation.

Abstract: A method, an apparatus for encoding at least one component of at least one attribute of an animated 3D object and a method and an apparatus for decoding at least one component of at least one attribute of an animated 3D object are disclosed. The at least one component of the at least one attribute of the animated 3D object is encoded by reframing values of the attributes into a first subset and a second subset, wherein the first subset of values comprises values of the at least one component being in a range of values, and the second subset of values comprising values of the at least one component being outside the range of values, and encoding the first subset and the second subset of values.

Abstract: At least one embodiment relates to a method and an apparatus for reconstructing an occupancy map comprising occupancy data of a volumetric content, wherein reconstructing the occupancy map comprises: —decoding the occupancy map at a first resolution, —determining a scale factor as a function of the first resolution, —upscaling the occupancy map by the scale factor, using a neural network.

Abstract: A virtual reality (VR) or augmented reality (AR) system detects through a camera when a user's hand positions match a predefined position and in response thereto renders an overlay including a crown with which the user can interact to lock onto an object or scene. The system then detects and renders a centre indicator of the crown, tracking the user's hands, enables or disables actions depending on the position of the centre indicator relative to a neutral zone, responds to user hand movement to implement actions, and also detects unlock of the object or scene.

Abstract: A virtual reality (VR) or augmented reality (AR) system detects through a camera w lien a user's hand positions match a predefined position and in response thereto renders an Overlay including a crown with which the user can interact to lock onto an object or scene The system then detects and renders a centre indicator of the crown, tracking the user's hands, enables or disables actions depending on the position of the centre indicator relative to a neutral zone, responds to user hand movement to implement actions, and also detects unlock of the object or scene

Abstract: A method and apparatus for detecting a main lighting direction from the input image, which corresponds to a key light. The system is operative to nm on data-parallel architectures allows for incoming light direction estimation in real-time. More particularly, the method and apparatus detect a key, or principal light direction relative to the position/orientation of an acquisition device. It method involves image analysis to find a maximum intensity value, maximal values filtering, and conversion of the input image position to a direction in space.

Abstract: The present invention relates to a glossy part of radiation is estimated coming from a surface illuminated by area light source(s) having source surface(s) (A) bounded by edge curves, by determining integrand function(s) representative of that glossy part. The latter corresponding to an integration of the integrand function along the edge curves. In this respect, the integrand function(s) is/are approximated by means of peak-shape function(s) having a known antiderivative over the edge curves, and the glossy part is computed from analytical expressions associated with integrations of the peak-shape function(s) along the edge curves. Such invention can offer efficient and accurate computation for specular part of reflection as well as glossy transmission, and is notably relevant to real-time rendering.

Abstract: A method and device for enriching the content associated with a first element of a depth map, the depth map being associated with a scene according to a point of view. Thereafter, at least a first information representative of a variation of depth in the first element in the space of the depth map is stored into the depth map.

Abstract: Shadow is computed in a lighted 3D scene, based on a depth map. For each depth map element, following geometric information is stored: depth value, coordinates of vertices and local depth variation of a surface element. Also, ray intersection is tested for a pixel with the surface element having depth computed from the depth and local depth variation, taking into account the coordinates of vertices. A minimum depth associated with the surface element is further computed from the geometric information, with which the depth of a pixel is compared. The pixel is classified as lit if the depth is lower than the minimum depth, and as shadowed if the depth is greater and if a ray intersection is found for the pixel with the surface element from the ray intersection testing. The invention can provide a fast solution for high-quality shadow.

Abstract: Shadow is computed in a lighted 3D scene, based on a depth map. For each depth map element, following geometric information is stored: depth value, coordinates of vertices and local depth variation of a surface element. Also, ray intersection is tested for a pixel with the surface element having depth computed from the depth and local depth variation, taking into account the coordinates of vertices. A minimum depth associated with the surface element is further computed from the geometric information, with which the depth of a pixel is compared. The pixel is classified as lit if the depth is lower than the minimum depth, and as shadowed if the depth is greater and if a ray intersection is found for the pixel with the surface element from the ray intersection testing. The invention can provide a fast solution for high-quality shadow.

Abstract: A method and apparatus for detecting a main lighting direction from the input image, which corresponds to a key light. The system is operative to nm on data-parallel architectures allows for incoming light direction estimation in real-time. More particularly, the method and apparatus detect a key, or principal light direction relative to the position/orientation of an acquisition device. It method involves image analysis to find a maximum intensity value, maximal values filtering, and conversion of the input image position to a direction in space.

Abstract: There is proposed a method of detecting a fiducial marker displayed on a display device (2) in a real world, wherein a portable device (1), comprising a camera and a marker detector unit, performs: obtaining current attribute information representative of a current value of at least one modifiable attribute associated with the displayed fiducial marker (5); detecting the displayed fiducial marker in an image displayed on the display device, according to the current attribute information; computing pose information representative of a pose of the portable device with regard to the displayed fiducial marker in the real world, according to the current attribute information and the detected displayed fiducial marker; and obtaining first new attribute information representative of a first new value of the at least one modifiable attribute, the first new value depending on the computed pose information.

Abstract: A method and device for establishing a frontier between a first object and at least a second object of a scene in the space of a depth map, at least a part of the first object and at least a part of the at least a second object being visible from the point of view associated with the depth map through a set (3) of elements of the depth map.

Abstract: A glossy part of a radiation coming from a surface illuminated by area light source(s) (21) having source surface(s) (A) bounded by edge curves (210) is estimated, by determining one or more integrand function(s) representative of that glossy part, the latter corresponding to an integration of the integrand function along the edge curves. In this respect, the integrand function(s) is/are approximated by means of at least one ellipsoid-based-peak-shape function(s) having a null first derivative at integration domain bounds, and the glossy part is computed from one or more analytical expression associated with integrations of the ellipsoid-based-peak-shape function(s) along the edge curves.

Abstract: For rendering a specular part of a surface illuminated by an area light source (A), a viewing reflection vector (R) associated with an image to be rendered at a shading point (x) is established. For each spherical edge UiUi+1 of a projected area consisting in a projection of the light source onto a unit sphere centered on the shading point, a local radiance is established by: establishing a normalized projection vector S of the viewing reflection vector onto a plane defined by edge UiUi+1 and the shading point determining if point S associated with vector S lies inside UiUi+1, and if so, performing a halfway transform of Ui; S and Ui+1 and an edge integral on Ui; S and S, Ui+1. An iteration is performed over all edges and the local radiance is summed, the surface being rendered accordingly.

Abstract: A 3D scene illuminated by light sources is rendered on an image grid by path tracing. At least one ray originating from each grid pixel is traced in the 3D scene until it meets an object at a crossing point, that ray is bounced towards one of the light sources, a visibility test is made for that ray between the crossing point and that light source, and a contribution of that light ray is added at the crossing point in carrying out the rendering at the concerned pixel. The visibility tests are carried out over the pixels in a clustered way according to the light sources, the visibility tests being clustered in terms of computations and/or of memory storage in function of the light sources respectively associated with the visibility tests.

Abstract: An Apparatus for use in producing lighting effects comprising a plurality of graphic processing units, each graphic processing unit for jittering a first ray, having a direction, to result in a second ray, the second ray having a direction not the same as the first ray; and each graphic processing unit having a plurality of threads for processing rays for computing lighting effects such that the first ray is processed by a first thread and the second ray is processed in a thread adjacent to the first thread; and a memory for providing data for use in computing the lighting effects for the first ray and the second ray.

Abstract: Elementary geometries for rendering objects of a 3D scene are generated from input geometry data sets. Instructions of a source program are transformed into a code executable in a rendering pipeline by at least one graphics processor, by segmenting the source program into sub-programs, each adapted to process the input data sets, and by ordering the sub-programs in function of the instructions. Each ordered sub-program is configured in the executable code for being executed only after the preceding sub-program has been executed for all input data sets. Launching the execution of instructions to generate elementary geometries includes determining among the sub-programs a starting sub-program, deactivating all sub-programs preceding it and activating it as well as all sub-programs following it. Modularity is thereby introduced in generating elementary geometries, allowing time-efficient lazy execution of grammar rules.

Abstract: A particular implementation selects two or more fiducial markers to be embedded into a video to convey information. Specifically, the translation, scaling and rotation between a reference marker and a secondary marker can be used to transmit information. When more information needs to be embedded, more secondary markers can be used. The transformation between the fiducial markers can also evolve over time as the information to be embedded evolves over time. At the receiving side, a reader device captures a video including multiple fiducial markers and determines the translation, scaling and rotation between the fiducial markers. Based on the transformation of the fiducial markers, the reader device can retrieve the information embedded in the captured video by the fiducial markers.

Abstract: Method and device for processing a geometry image generated from a mesh associated with a 3D scene and comprising a plurality of charts that each represents a part of the 3D scene, the method comprising computing a reference direction from mesh coordinates associated with a current pixel and mesh coordinates associated with a first pixel, the first pixel corresponding to a pixel of the border of the first chart located along a determined direction having as origin the current pixel; comparing the reference direction with a set of candidate directions being each computed from the mesh coordinates associated with the at least one current pixel and indirection mesh coordinates associated with one pixel of the neighbourhood of the first pixel, the indirection mesh coordinates corresponding to mesh coordinates of a pixel of the border a second chart corresponding to the pixel of the neighbourhood of the first pixel; and selecting a pixel of the border of the second chart according to the comparison result.