Disney Enterprises, Inc.

Eidgenossische Technische Hochschule Zurich

Fraunhofer-Gesellschaft Zur Foerderung Der Angewandten Forschung E.v.

Eth Zurich

The Provost, Fellows, Foundation Scholars, and the Other Members of Board, of the College of the Holy and Undivided Trinity of Queen Elizabeth Near Dublin

Aljosa A Smolic

Nikolce Stefanoski

Tunc Ozan Aydin

Oliver Wang

Alexander Sorkine Hornung

Markus H Gross

Manuel Lang

Samir Mahmalat

Karsten Mueller

Miquel Angel Farre Guiu

Markus Gross

David S Monaghan

Anselm Grundhofer

Marc Pollefeys

Yagiz Aksoy

Adriano Galati

Konstantinos Amplianitis

Nicolas Märki

Jan Ondrej

Daniel Luginbuhl

Yongzhe Wang

Jan Ruegg

Kristina Dix

Jing Liu

The method comprising providing a plurality of images of a scene captured by a plurality of image capturing devices (); providing silhouette information of at least one object in the scene (); generating a point cloud for the scene in 3D space using the plurality of images (); extracting an object point cloud from the generated point cloud, the object point cloud being a point cloud associated with the at least one object in the scene (); estimating a 3D shape volume of the at least one object from the silhouette information (); and combining the object point cloud and the shape volume of the at least one object to generate a three-dimensional model (). An apparatus for generating a 3D model, and a computer readable medium for generating the 3D model.

Method and apparatus for generating a three-dimensional model

Techniques are disclosed for view generation based on a video coding scheme. A bitstream is received that is encoded based on the video coding scheme. The bitstream includes video, quantized warp map offsets, and a message of a message type specified by the video coding scheme. Depth samples decoded from the first bitstream are interpreted as quantized warp map offsets, based on a first syntax element contained in the message. Warp maps are generated based on the quantized warp map offsets and a second syntax element contained in the message. Views are generated using image-domain warping and based on the video and the warp maps.

Signaling warp maps using a high efficiency video coding (HEVC) extension for 3D video coding

Disclosed is a system for linking transmedia content subsets. A memory stores a plurality of transmedia content data items and associated linking data, which define time-ordered content links between the transmedia content data items. The transmedia content data items are arranged into linked transmedia content subsets comprising different groups of the transmedia content data items and different content links therebetween; a transmedia content model that represents the transmedia content data items as nodes and the content links between the transmedia content data items as edges in one or more time-varying graphs. A processor is configured to associate the transmedia content data items with the time-ordered content links and store the linking data in the memory. It assigns the transmedia content data items to nodes of a graph structure, assign the time-ordered content links to edges of the graph structure, and store them in the transmedia content model.

User modelling and metadata of transmedia content data

The disclosure describes a high dynamic range video coding pipeline that may reduce color artifacts and improve compression efficiency. The disclosed pipeline separates the luminance component from the chrominance components of an input signal (e.g., an RGB source video) and applies a scaling of the chrominance components before encoding, thereby reducing perceivable color artifacts while maintaining luminance quality.

Pipeline for high dynamic range video coding based on luminance independent chromaticity preprocessing

A video coding pipeline is provided that can accommodate high dynamic range (HDR) and wide color gamut (WCG) content at a fixed bitrate. The video coding pipeline relies on separate chromaticity and luminance-specific transforms in order to process image content. Image content may be converted into a nearly perceptually uniform color space for coding in constant luminance. Moreover, chromaticity transforms are utilized which reduce coding errors in the chroma components (at the fixed bitrate) by enlarging the distribution of code words for compression.

Perceptual color transformations for wide color gamut video coding

Methods and systems described herein detect object boundaries of videos. A window around the pixel may be followed in adjacent image frames of the image frame to determine object boundaries. Inconsistencies in image patches over a temporal window are detected, and each pixel of the image frame of a video is assigned an object boundary probability. The pixel may belong to a texture edge if the window content does not change throughout the adjacent image frames, or the pixel may belong to an object boundary if the window content changes. A probability value indicating the likelihood of the pixel belonging to an object boundary is determined based on the window content change and is assigned to the corresponding pixel.

Methods and systems of detecting object boundaries

This disclosure related to systems and methods of palette-based color editing. A set of principle colors may be identified from among individual colors of individual pixels of an image. Color distributions about the individual principle colors may be determined. An individual color distribution may include a homogenous range of colors that may vary with respect to an individual principle color. Pixels may be associated with one or more pixel groups based on correspondences between individual colors of the individual pixels and individual colors included in the individual color distributions corresponding to the individual pixel groups. Color editing may be effectuated by modifying colors of pixels in a given group independently from other colors of other pixels in other groups.

System and method facilitating palette-based color editing

Methods and systems for calibrating devices reproducing high dimensional data, such as calibrating High Dynamic Range (HDR) displays that reproduce chromatic data. Methods include mapping input data into calibrated data using calibration information retrieved from spatial data structures that encode a calibration function. The calibration function may be represented by any multidimensional scattered data interpolation methods such as Thin-Plate Splines. To efficiently represent and access the calibration information in runtime, the calibration function is recursively sampled based on guidance dataset. In an embodiment, an HDR display may be adaptively calibrated using a dynamic color guidance dataset and dynamic spatial data structures.

Chromatic Calibration of an HDR display using 3D octree forests

As described herein, an electronic device with a display screen may simulate the color diffusion that occurs in a physical painting process. For instance, the user may perform one or more actions that simulate a brushstroke on the display screen such as swiping a touch-sensitive area or dragging a cursor across the screen. The electronic device then calculates a geodesic distance between a pixel inside a region defined by the brushstroke and a pixel located outside this region based on the physical distance between the two pixels and a weighting factor that varies depending on whether an image boundary is between the two pixels. Based on the geodesic distance, the electronic device uses a color diffusion relationship that defines the effect of the color of the brushstroke on the pixel and a time delay controlling when the color of the brushstroke reaches the pixel in order to simulate color diffusion.

Simulating color diffusion in a graphical display

An intermediate view synthesis apparatus for synthesizing an intermediate view image from a first image corresponding to a first view and a second image corresponding to a second view different from the first view, the first and second images including depth information, wherein the second image being is divided-up into a non-boundary portion, and a foreground/background boundary region, wherein the intermediate view synthesis apparatus is configured to project and merge the first image and the second image into the intermediate view to obtain an intermediate view image, with treating the foreground/background boundary region subordinated relative to the non-boundary portion. A multi-view data signal extraction apparatus for extracting a multiview data signal from a multi-view representation including a first image corresponding to a first view and a second image corresponding to a second view being different from the first view is also described, the first and second images including depth information.

Intermediate view synthesis and multi-view data signal extraction

Embodiments provide techniques for creating a composite video stream. Additionally, a first selection of pixels from the first video stream and a second selection of pixels from the second video stream are received. Here, both the first selection of pixels and the second selection of pixels indicate pixels that are to be included in the composite video stream. Embodiments identify a plurality of spatiotemporal seams across the first video stream and the second video stream, based at least in part on the first selection of pixels and the second selection of pixels. The first video stream and the second video stream are then composited into the composite video stream, by joining frames from the first video stream and the second video stream at the identified plurality of spatiotemporal seams.

Spatio-temporal video compositing

An approach for determining transducer functions for mapping objective image attribute values to estimated subjective attribute values. The approach includes determining objective attribute values for each of one or more aesthetic attributes for each image in a first set of images. The approach further includes determining, for each aesthetic attribute, a mapping from the objective attribute values to respective estimated subjective attribute values based on the objective attribute values and corresponding experimentally-determined attribute values. Using the determined mappings, aesthetic signatures, which include estimates of subjective image aesthetics across multiple dimensions, may be generated.

Growing community of inventors

Zurich, Switzerland

Aljosa A Smolic