ETH ZURICH (EIDGENOSSISCHE TECHNISCHE HOCHSCHULE ZURICH) (Suisse)
Inventeur(s)
Bradley, Derek Edward
Urnau Gotardo, Paulo Fabiano
Wang, Daoye
Zoss, Gaspard
Abrégé
Techniques are disclosed for generating photorealistic images of objects, such as heads, from multiple viewpoints. In some embodiments, a morphable radiance field (MoRF) model that generates images of heads includes an identity model that maps an identifier (ID) code associated with a head into two codes: a deformation ID code encoding a geometric deformation from a canonical head geometry, and a canonical ID code encoding a canonical appearance within a shape-normalized space. The MoRF model also includes a deformation field model that maps a world space position to a shape-normalized space position based on the deformation ID code. Further, the MoRF model includes a canonical neural radiance field (NeRF) model that includes a density multi-layer perceptron (MLP) branch, a diffuse MLP branch, and a specular MLP branch that output densities, diffuse colors, and specular colors, respectively. The MoRF model can be used to render images of heads from various viewpoints.
ETH ZURICH (EIDGENOSSISCHE TECHNISCHE HOCHSCHULE ZURICH) (Suisse)
Inventeur(s)
Bradley, Derek Edward
Chandran Prashanth
Urnau Gotardo, Paulo Fabiano
Zoss, Gaspard
Abrégé
A technique for generating a sequence of geometries includes converting, via an encoder neural network, one or more input geometries corresponding to one or more frames within an animation into one or more latent vectors. The technique also includes generating the sequence of geometries corresponding to a sequence of frames within the animation based on the one or more latent vectors. The technique further includes causing output related to the animation to be generated based on the sequence of geometries.
ETH ZURICH (EIDGENOSSISCHE TECHNISCHE HOCHSCHULE ZURICH) (Suisse)
Inventeur(s)
Bradley, Derek Edward
Chandran, Prashanth
Urnau Gotardo, Paulo Fabiano
Zoss, Gaspard
Abrégé
A technique for synthesizing a shape includes generating a first plurality of offset tokens based on a first shape code and a first plurality of position tokens, wherein the first shape code represents a variation of a canonical shape, and wherein the first plurality of position tokens represent a first plurality of positions on the canonical shape. The technique also includes generating a first plurality of offsets associated with the first plurality of positions on the canonical shape based on the first plurality of offset tokens. The technique further includes generating the shape based on the first plurality of offsets and the first plurality of positions.
G06F 17/00 - TRAITEMENT ÉLECTRIQUE DE DONNÉES NUMÉRIQUES Équipement ou méthodes de traitement de données ou de calcul numérique, spécialement adaptés à des fonctions spécifiques
G06V 10/46 - Descripteurs pour la forme, descripteurs liés au contour ou aux points, p.ex. transformation de caractéristiques visuelles invariante à l’échelle [SIFT] ou sacs de mots [BoW]; Caractéristiques régionales saillantes
ETH ZURICH (EIDGENOSSISCHE TECHNISCHE HOCHSCHULE ZURICH) (Suisse)
Inventeur(s)
Zoss, Gaspard
Bradley, Derek Edward
Chandran, Prashanth
Urnau Gotardo, Paulo Fabiano
Sifakis, Eftychios
Abrégé
Techniques are disclosed for re-aging images of faces and three-dimensional (3D) geometry representing faces. In some embodiments, an image of a face, an input age, and a target age, are input into a re-aging model, which outputs a re- aging delta image that can be combined with the input image to generate a re-aged image of the face. In some embodiments, 3D geometry representing a face is re-aged using local 3D re-aging models that each include a blendshape model for finding a linear combination of sample patches from geometries of different facial identities and generating a new shape for the patch at a target age based on the linear combination. In some embodiments, 3D geometry representing a face is re-aged by performing a shape- from- shading technique using re-aged images of the face captured from different viewpoints, which can optionally be constrained to linear combinations of sample patches from local blendshape models.
ETH ZURICH (EIDGENOSSISCHE TECHNISCHE HOCHSCHULE ZURICH) (Suisse)
Inventeur(s)
Bradley, Derek Edward
Urnau Gotardo, Paulo Fabiano
Zoss, Gaspard
Chandran, Prashanth
Abrégé
A technique for performing style transfer between a content sample and a style sample is disclosed. The technique includes applying one or more neural network layers to a first latent representation of the style sample to generate one or more convolutional kernels. The technique also includes generating convolutional output by convolving a second latent representation of the content sample with the one or more convolutional kernels. The technique further includes applying one or more decoder layers to the convolutional output to produce a style transfer result that comprises one or more content-based attributes of the content sample and one or more style- based attributes of the style sample.
Techniques are disclosed for changing the identities of faces in video frames and images. In embodiments, three-dimensional (3D) geometry of a face is used to inform the facial identity change produced by an image-to-image translation model, such as a comb network model. In some embodiments, the model can take a two-dimensional (2D) texture map and/or a 3D displacement map associated with one facial identity as inputs and output another 2D texture map and/or 3D displacement map associated with a different facial identity. The other 2D texture map and/or 3D displacement map can then be used to render an image that includes the different facial identity.
Techniques are disclosed for capturing facial appearance properties. In some examples, a facial capture system includes light source(s) that produce linearly polarized light, at least one camera that is cross-polarized with respect to the polarization of light produced by the light source(s), and at least one other camera that is not cross-polarized with respect to the polarization of the light produced by the light source(s). Images captured by the cross-polarized camera(s) are used to determine facial appearance properties other than specular intensity, such as diffuse albedo, while images captured by the camera(s) that are not cross-polarized are used to determine facial appearance properties including specular intensity. In addition, a coarse-to-fine optimization procedure is disclosed for determining appearance and detailed geometry maps based on images captured by the cross-polarized camera(s) and the camera(s) that are not cross-polarized.
G06T 19/00 - Transformation de modèles ou d'images tridimensionnels [3D] pour infographie
G06T 7/80 - Analyse des images capturées pour déterminer les paramètres de caméra intrinsèques ou extrinsèques, c. à d. étalonnage de caméra
G01B 11/245 - Dispositions pour la mesure caractérisées par l'utilisation de techniques optiques pour mesurer des contours ou des courbes en utilisant plusieurs transducteurs fixes fonctionnant simultanément
G03B 11/00 - Filtres ou autres intercepteurs spécialement adaptés pour les besoins photographiques
ABSTRACT OF THE DISCLOSURE Techniques are disclosed for interactive editing of virtual three-dimensional scenes. In the disclosed techniques, rendering is divided into (1) an interactive phase during which a user interactively edits a virtual scene while preview image frames are rendered using a modified ray tracing technique, and (2) a refinement phase during which full ray tracing is performed to show the user a final rendered image frame. The modified ray tracing technique may limit the number of bounces of light rays and/or the computations performed at each bounce, thereby reducing computational expense relative to a full ray tracing technique. Further, the modified ray tracing technique may be user-selectable and associated with a particular department within an animation studio. Date Recue/Date Received 2021-01-06
According to one implementation, a cloud-based system for performing cloud- based image rendering for video stream enrichment includes a video forwarding unit and a video enrichment unit. The video forwarding unit is configured to detect one or more non- interactive video player(s) linked to the video forwarding unit over a communication network, forward a video stream to the non-interactive video player(s), and forward the video stream to the video enrichment unit. The video enrichment unit is configured to receive the video stream, detect one or more interactive video player(s) linked to the video enrichment unit over the communication network, identify a video enhancement corresponding to one or more customizable video segment(s) in the video stream, insert a rendered video enhancement into the one or more customizable video segment(s) to produce an enriched video stream, and distribute the enriched video stream to one or more of the interactive video player(s).
H04N 21/2343 - Traitement de flux vidéo élémentaires, p.ex. raccordement de flux vidéo ou transformation de graphes de scènes MPEG-4 impliquant des opérations de reformatage de signaux vidéo pour la distribution ou la mise en conformité avec les requêtes des utilisateurs finaux ou les exigences des dispositifs des utilisateurs finaux
H04H 60/33 - Dispositions de contrôle du comportement ou des opinions des utilisateurs
H04N 21/258 - Gestion de données liées aux clients ou aux utilisateurs finaux, p.ex. gestion des capacités des clients, préférences ou données démographiques des utilisateurs, traitement des multiples préférences des utilisateurs finaux pour générer des données co
H04N 21/40 - Dispositifs clients spécialement adaptés à la réception de contenu ou à l'interaction avec le contenu, p.ex. boîtier décodeur [STB]; Leurs opérations
H04N 21/472 - Interface pour utilisateurs finaux pour la requête de contenu, de données additionnelles ou de services; Interface pour utilisateurs finaux pour l'interaction avec le contenu, p.ex. pour la réservation de contenu ou la mise en place de rappels, pour la requête de notification d'événement ou pour la transformation de contenus affichés
H04N 21/63 - Signalisation de contrôle entre des éléments du client, serveur et réseau; Procédés liés au réseau pour la distribution de vidéo entre serveur et clients, p.ex. transmission de la couche de base et des couches d’amélioration sur des voies de transmission différentes, mise en œuvre d’une communication pair à pair via Interne; Protocoles de communication; Adressage
H04N 21/8545 - Création de contenu pour générer des applications interactives
10.
COORDINATION OF MEDIA CONTENT DELIVERY TO MULTIPLE MEDIA PLAYERS
A system for synchronizing media content playout includes a computing platform having a hardware processor and a system memory storing a software code. The hardware processor executes the software code to receive a first state message from a first media player playing a first media content and a second state message from a second media player playing a second media content, the first media content and the second media content being the same media content. The software code further determines a coordination state for playout of the first media content and the second media content based on one or more of the first and second state messages, and transmits a first coordination message including the coordination state to the first media player and a second coordination message including the coordination state to the second media player to synchronize playout of the first media content and the second media content.
G11B 27/10 - Indexation; Adressage; Minutage ou synchronisation; Mesure de l'avancement d'une bande
H04N 21/242 - Procédés de synchronisation, p.ex. traitement de références d'horloge de programme [PCR]
H04N 21/4788 - Services additionnels, p.ex. affichage de l'identification d'un appelant téléphonique ou application d'achat communication avec d'autres utilisateurs, p.ex. discussion en ligne
H04N 21/6547 - Transmission du serveur vers le client comprenant des paramètres, p.ex. pour l'initialisation du client
H04N 21/6587 - Paramètres de contrôle, p.ex. commande de lecture à vitesse variable ("trick play") ou sélection d’un point de vue
11.
METHODS AND SYSTEMS FOR 3D ANIMATION UTILIZING UVN TRANSFORMATION
A system and method for 3D animation utilizing UVN transformation includes generation of head meshes in Cartesian space, transformation of head mesh vertices into UVN coordinate space, mapping of vertices to their closest UV coordinates on the surface, with signed distances becoming their N coordinates, sculpting flattened, square UVN meshes, transforming said meshes back to Cartesian space by evaluating the parameterized surface at the new UV coordinates, and scaling surface normal by the new N coordinate and adding to the surface positions.
Systems, tools and methods for 3D animation provided including: creating stereoscopic effect in 3D animation in a shot; determining maximum parallax in 3D animation; representation of stereo effect on a non-stereoscopic monitor in 3D animation; producing a digital contact sheet created for viewing in 3D animation; correcting for holes created by missing pixel information from a left camera perspective in 3D animation; real-time compositing of multiple stereo camera views in 3D animation; and emulation of multi-cam rig in 3D animation.
G06T 13/40 - Animation tridimensionnelle [3D] de personnages, p.ex. d’êtres humains, d’animaux ou d’êtres virtuels
H04N 13/122 - Raffinement de la perception 3D des images stéréoscopiques par modification du contenu des signaux d’images, p.ex. par filtrage ou par ajout d’indices monoscopiques de profondeur
H04N 13/268 - Générateurs de signaux d’images avec conversion d’images monoscopiques en images stéréoscopiques au moyen du rendu basé sur une image de profondeur
13.
ORDERING RAYS IN RENDERED GRAPHICS FOR COHERENT SHADING
There is provided a system and a method for ordering rays in rendered graphics for coherent shading. The method comprises recording, using the processor, intersection points for each of a plurality of directional queries in the memory, wherein each of the plurality of directional queries has one intersection point, organizing, using the processor, the intersection points in the memory into a plurality of elements, and grouping, using the processor, the intersection points in the memory by shading context. The method may further comprise shading the intersection points, wherein the shading is performed on a plurality of elements substantially concurrently. The shading context may include a volume of intersection points. In another implementation, the shading context may be one of texture ID, material ID, and element ID. Additionally, the texture ID may correspond to a mesh face ID.
A system and method for leveraging grid computing for node based interactive workflows is disclosed. A server system spawns a server process that receives node graph data and input attributes from a computing device, processes the data, caches the processed data, and transmits the processed data over a network to a computing device. The computing device runs a node graph application instance comprising proxy nodes configured to initiate a request to process node graph data at the server system. The server processed node graph data is displayed on the computing device. A plurality of computing devices may collaborate on a complex node graph where the node graph data processing is distributed over a plurality of servers.
G06F 15/16 - Associations de plusieurs calculateurs numériques comportant chacun au moins une unité arithmétique, une unité programme et un registre, p.ex. pour le traitement simultané de plusieurs programmes
Some aspects of the disclosure include systems and methods for grouping rays into sets according to their directions. In some cases, the rays of the directional sets may then be organized into a hierarchy according to their origins and bounding cones are generated for the hierarchy nodes. The resulting bounding cone hierarchy may be intersected with a bounding volume hierarchy or other scene hierarchy.
A method is provided for a streaming hierarchy traversal renderer with particular application for feature films and other demanding content creation using scenes of high complexity that cannot fit in memory. The renderer organizes scene geometry into a spatial hierarchy, generates directional queries to be traced in the spatial hierarchy, performs a streaming hierarchy traversal over the directional queries, and uses the results of the directional queries to shade or render the scene. The traversal performs a single pass over the directional queries for splitting into one child stream of directional queries for each child node at each scene node in the hierarchy. A prioritized traversal of the hierarchy may also be carried out using various cost-metrics for optimized parallelism. The rendering may also bounce the directional queries to provide multi-pass global illumination.
A method is provided for streaming light propagation with particular application for feature films and other demanding content creation using scenes of high complexity requiring art directed global illumination. By attaching a data recording shader or equivalent functionality to any tracing based renderer that can provide multi-pass global illumination, the complete set of light bounce propagation records and the set of emissive samples for a particular rendering can be recorded to memory or disk. A user may edit the emissive samples to adjust the lighting environment, including modifying light source color and intensity and even moving and adding new emissive samples. To relight the scene, the edited emissive samples are processed through the propagation records using a streaming multiply-and-add operation amenable to high levels of parallelization, avoiding a costly re-rendering of the scene and providing a final quality result in interactive time.
A method is provided for integration cone tracing with particular application for feature films and other demanding content creation using scenes of high complexity requiring global illumination. Instead of using a conventional noise prone ray tracer, cones are intersected with a scene bounding hierarchy to determine intersecting scene geometry, and integration results are computed by directional sampling within the cones. As a result, the working data set may be reduced as the rendering may begin with a smaller set of cones as compared to the large number of rays required for acceptable filtering in a conventional ray tracer. Furthermore, by refining the cones during the rendering only on an as- needed basis according to an acceptable noise threshold and by sharing secondary cone bounces among primary cones, the processing workload and data set requirements may be kept to a reasonable level even for multiple global illumination passes.
A system and method for automatically repositioning virtual and physical elements in a scene. The system and method being configured to receive a video frame, receive data, including position data, describing a first element to be imaged in the video frame, receive data, including position data, describing a second element to be imaged in the video frame, assign a dynamic status to the first element and automatically reposition at least the first element to create a modified video frame.
There is provided a system and method for communicating with a first peripheral device, of a plurality of peripheral devices, using a touch-sensitive system that has a processor and a touch surface. According to an exemplary embodiment, a method includes detecting, using the processor, a plurality of touches on the touch surface of the touch-sensitive system that are made by the first peripheral device. The method further includes identifying, using the processor, the first peripheral device based on the plurality of touches on the touch surface of the touch-sensitive system that are made by the first peripheral device. The method additionally includes communicating data, using th processor, to a receptive circuit of the first peripheral device in response to the identifying of the first peripheral device.
An infant bodysuit having a pair of rows of snap sockets either one of which can receive a curved row of snaps studs, the rows of snap sockets and snap studs being provided along a gentle curve that is easy for a caregiver to match up the studs and sockets. Reinforcement, through a woven fabric facing, is provided in the region of the snap sockets on the front panel to provide two-dimensional stability throughout the region. Rib binding is used along the leg openings and covers the facing material for improved comfort to the infant. A flat, straight edge bottom is provided along the bottom edge of the front panel to reduce bulkiness. An improved leg opening is achieved by significantly narrowing the width of the front panel from the top of the leg opening down to the attachment portion.
Embodiments of this invention relate to preprocessing video such that visual elements, such as advertisements, can be inserted at a later point in time when the video is requested by a user. In an embodiment, a video and target data is received. The video is analyzed to determine how a target moves and changes over time. Metadata describing how the target moves and changes over time is stored. When a user requests an on-demand video such as from a video sharing site, a visual element is inserted into the video. The visual elements move and change as defined in the stored metadata. In this way, advertisements can be inserted into on-demand video such as video from a video sharing website.
G06F 16/787 - Recherche de données caractérisée par l’utilisation de métadonnées, p.ex. de métadonnées ne provenant pas du contenu ou de métadonnées générées manuellement utilisant des informations géographiques ou spatiales, p.ex. la localisation
H04N 5/272 - Moyens pour insérer une image de premier plan dans une image d'arrière plan, c. à d. incrustation, effet inverse
23.
GENERATION OF THREE-DIMENSIONAL MOVIES WITH IMPROVED DEPTH CONTROL
Techniques for creating 3-D movies allow improved control over camera positioning parameters and editing of depth in post process to provide for a smoother variation in the viewer's convergence distance and a more pleasant viewing experience. A director can define reference parameters related to a desired viewing experience, and camera positioning parameters are derived therefrom. A depth script specifying piecewise continuous variations in reference parameters can be applied in post process to generate 3-D shots, scenes, or movies. These techniques can be applied in both computer generated and live action 3-D movies.
24.
SYSTEM AND/OR METHOD FOR DISTRIBUTING MEDIA CONTENT
Delivering media contents In a media distribution system, where the content comprises a plurality of segments. Selectively protecting the plurality of segments by suitable encryption/encoding processes and associating content gateway to the protected segments. And distributing the content Including the protected and unprotected segments wherein the client device can decrypt the protected segments only upon accessing the gateway. The content gateways constitute advertisements and are selected based on profile of the user accessing the content and charging the advertisers for accessing the advertisements and thus rendering the contents free of charge to users.
H04N 21/266 - Gestion de canal ou de contenu, p.ex. génération et gestion de clés et de messages de titres d'accès dans un système d'accès conditionnel, fusion d'un canal de monodiffusion de VOD dans un canal multidiffusion
25.
SYSTEM AND METHOD OF PLAYBACK AND FEATURE CONTROL FOR VIDEO PLAYERS
A method and a system (120) of displaying a user interface to control playback and features that may be associated with a prerecorded media. A media player (100), such as a DVD player, a personal computer, a home media server, a high definition video player, an optical player, a hard drive based player, or a software DVD-ROM player receives streams of video from different media and displays its content. Simultaneously, and without interrupting the video playback, a user interface is overlaid on the video image. The user interface may include menu selections to control the playback of the video including scene selection, settings, and viewing rights. The user interface may include menu selections to control features associated with the video such as Documentaries, Games, Purchases, Activities, Commentaries, Outtakes, Karaoke, Trailers, Songs, Wishlists, and Events.
A software computing based environment (10) for providing secured authentication of media (12) downloaded from a network or loaded from a media player includes two peer-mode operating virtual machines (22, 24). The low- level virtual machine (22) provides decoding and decryption functions whereas the high-level virtual machine (24) provides application level functions such as user interface, input/output.
G06F 12/14 - Protection contre l'utilisation non autorisée de mémoire
H04L 9/32 - Dispositions pour les communications secrètes ou protégées; Protocoles réseaux de sécurité comprenant des moyens pour vérifier l'identité ou l'autorisation d'un utilisateur du système
Video player (20) plays vides (30) using media (10). It causes a menu to display (40), recognizes triggers (50) and based on user (15) input skips segments (60) of video, inserts graphics 70 and plays a game.
A media playback device capable of displaying multiple streams simultaneously and with expanded picture-in-picture capabilities is provided. The placement, size, aspect ratio, cropping, scale, transparency, tint, contrast, and cropping of the media can be set or adjusted arbitrarily. Furthermore, the audio may be mixed between separate tracks accompanying the video streams and may also be set or adjusted arbitrarily. Each variable can be dynamically changed during playback through either automated or user-initiated means. A system and method are provided for simultaneously displaying a first video stream and at least a second video stream on a display comprising the steps of feeding the video streams into a video player; providing control of the display of the video streams; displaying a first video stream substantially across the display; and displaying the other video streams in a secondary display.
H04N 21/43 - Traitement de contenu ou données additionnelles, p.ex. démultiplexage de données additionnelles d'un flux vidéo numérique; Opérations élémentaires de client, p.ex. surveillance du réseau domestique ou synchronisation de l'horloge du décodeur; Intergiciel de client
G11B 27/10 - Indexation; Adressage; Minutage ou synchronisation; Mesure de l'avancement d'une bande