Adobe, Inc.

Haoliang Wang

Viswanathan Swaminathan

Stefano Petrangeli

Jennifer Anne Healey

Saayan Mitra

Ding Zhang

Na Wang

Ryan A Rossi

Georgios Theocharous

Gang Wu

Gwendal Simon

Zhao Song

Ran Xu

Yang Li

YoungJoong Kwon

In implementations of systems for estimating three-dimensional trajectories of physical objects, a computing device implements a three-dimensional trajectory system to receive radar data describing millimeter wavelength radio waves directed within a physical environment using beamforming and reflected from physical objects in the physical environment. The three-dimensional trajectory system generates a cloud of three-dimensional points based on the radar, each of the three-dimensional points corresponds to a reflected millimeter wavelength radio wave within a sliding temporal window. The three-dimensional points are grouped into at least one group based on Euclidean distances between the three-dimensional points within the cloud. The three-dimensional trajectory system generates an indication of a three-dimensional trajectory of a physical object corresponding to the at least one group using a Kalman filter to track a position and a velocity a centroid of the at least one group in three-dimensions.

Systems for estimating three-dimensional trajectories of physical objects

Embodiments described herein provide methods and systems for facilitating actively-learned context modeling. In one embodiment, a subset of data is selected from a training dataset corresponding with an image to be compressed, the subset of data corresponding with a subset of data of pixels of the image. A context model is generated using the selected subset of data. The context model is generally in the form of a decision tree having a set of leaf nodes. Entropy values corresponding with each leaf node of the set of leaf nodes are determined. Each entropy value indicates an extent of diversity of context associated with the corresponding leaf node. Additional data from the training dataset is selected based on the entropy values corresponding with the leaf nodes. The updated subset of data is used to generate an updated context model for use in performing compression of the image.

Actively-learned context modeling for image compression

Methods, system, and computer storage media are provided for novel view synthesis. An input image depicting an object is received and utilized to generate, via a neural network, a target view image. In exemplary aspects, additional view images are also generated within the same pass of the neural network. A loss is determined based on the target view image and additional view images and is used to modify the neural network to reduce errors. In some aspects, a rotated view image is generated by warping a ground truth image from an initial angle to a rotated view angle that matches a view angle of an image synthesized via the neural network, such as a target view image. The rotated view image and the synthesized image matching the rotated view angle (e.g., a target view image) are utilized to compute a rotational loss.

View synthesis with spatial and rotational consistency

Embodiments are disclosed for lossless image compression using block-based prediction and context adaptive entropy coding. A method of lossless image compression using block-based prediction and context adaptive entropy coding comprises dividing an input image into a plurality of blocks, determining a pixel predictor for each block based on a block strategy, determining a plurality of residual values using the pixel predictor for each block, selecting a subset of features associated with the plurality of residual values, performing context modeling on the plurality of residual values based on the subset of features to identify a plurality of residual clusters, and entropy coding the plurality of residual clusters.

Lossless image compression using block based prediction and optimized context adaptive entropy coding

In implementations of systems for digital image compression using context-based pixel predictor selection, a computing device implements a compression system to receive digital image data describing pixels of a digital image. The compression system groups first differences between values of the pixels and first prediction values of the pixels into context groups. A pixel predictor is determined for each of the context groups based on a compression criterion. The compression system generates second prediction values of the pixels using the determined pixel predictor for pixels corresponding to the first differences included in each of the context groups. Second differences between the values of the pixels and the second prediction values of the pixels are grouped into different context groups. The compression system compresses the digital image using entropy coding based on the different context groups.

Systems for digital image compression using context-based pixel predictor selection

The present disclosure describes multi-stage image editing techniques to improve detail and accuracy in edited images. An input image including a target region to be edited and an edit parameter specifying a modification to the target region are received. A parsing map of the input image is generated. A latent representation of the parsing map is generated. An edit is applied to the latent representation of the parsing map based on the edit parameter. The edited latent representation is input to a neural network to generate a modified parsing map including the target region with a shape change according to the edit parameter. Based on the input image and the modified parsing map, a masked image corresponding to the shape change is generated. Based on the masked image, a neural network is used to generate an edited image with the modification to the target region.

Techniques for image attribute editing using neural networks

A first device determines relative position data representative of a position of one or more other user devices relative to the first device. To determine relative position data between the first device and a second device, the first device determines a distance between the first device and the second device at a plurality of timestamps. Additionally, the first device determines movement data at each timestamp from one or more device sensors. The movement data at each corresponding timestamp may reflect movement of the first device and/or the second device between a prior timestamp and the corresponding timestamp. The first device computes relative position data for the second device by combining the distance measurements and movement data over the plurality of timestamps, for instance, through a process of sensor fusion. By computing the relative position data, the first device may determine a transformation that can be used to convert between a coordinate system of the second device and the coordinate system of the first device.

System for combining sensor data to determine a relative position

This disclosure describes embodiments of methods, systems, and non-transitory-computer readable media that personalize visual content for display on digital signage near a projected location of a person by mapping visual content to physical items selected by the person. In some examples, the disclosed system identifies physical items selected by a person based on signals from the physical items, such as signals emitted by RFID tags affixed to (or other devices associated with) the physical items. The disclosed system analyzes the collection of physical items&#x2014;as identified by the signals&#x2014;to tailor digital signage content specific to the person. The disclosed system further tracks the location of the person as the person moves through a physical space and interacts with the physical items. Based on the tracked positions, the disclosed system determines a digital sign in proximity to a predicted location of the person to display the personalized visual content.

Retrieving personalized visual content items in real time for display on digital-content-display devices within a physical space

The present disclosure relates to systems, non-transitory computer-readable media, and methods that iteratively select versions of augmented reality objects at augmented reality levels of detail to provide for download to a client device to reduce start-up latency associated with providing a requested augmented reality scene. In particular, in one or more embodiments, the disclosed systems determine utility and priority metrics associated with versions of augmented reality objects associated with a requested augmented reality scene. The disclosed systems utilize the determined metrics to select versions of augmented reality objects that are likely to be viewed by the client device and improve the quality of the augmented reality scene as the client device moves through the augmented reality scene. In at least one embodiment, the disclosed systems iteratively select versions of augmented reality objects at various levels of detail until the augmented reality scene is fully downloaded.

Low-latency adaptive streaming for augmented reality scenes

Techniques are disclosed for improving media content effectiveness. A methodology implementing the techniques according to an embodiment includes generating an intermediate representation (IR) of provided media content, the IR specifying editable elements of the content and maintaining a result of cumulative edits to those elements. The method also includes editing the elements of the IR to generate a set of candidate IR variations. The method further includes creating a set of candidate media contents based on the candidate IR variations, evaluating the candidate media contents to generate effectiveness scores, and pruning the set of candidate IR variations to retain a threshold number of the candidate IR variations as surviving IR variations associated with the highest effectiveness scores. The process iterates until either an effectiveness score exceeds a threshold value, the incremental improvement at each iteration falls below a desired value, or a maximum number of iterations have been performed.

Enhancing media content effectiveness using feedback between evaluation and content editing

Various embodiments describe data compression that implements vector quantization. A computer system generates a codebook for the vector quantization by iteratively clustering vectors representative of data that should be compressed. The iterative clustering uses geometric reasoning to avoid distance computations between vectors as appropriate, thereby reducing the latency associated with generating the codebook. Further, the system encodes the vectors based on the codebook. To do so, the computer system generates hashes of the vectors by applying locality sensitive hashing to these vectors. The hashes are compared and matched with hashes of codebook vectors. The computer system represents the vectors based on the matched codebook vectors.

Low-latency vector quantization for data compression

Various embodiments describe a dynamic reconfiguration of a media processing system to optimize a latency performance. In an example, a computer system accesses a current latency performance of the media processing system. The latency is associated with performing a codec process on a current configuration of the media processing system. The current configuration includes virtual machines. The computer system estimates, based on the current latency performance and on historical latency performances associated with the current configuration, a next latency performance of the media processing system. The computer system also identifies, from potential configurations, an updated configuration of the media processing system based on a difference between the next latency performance and a target latency performance and on historical performances associated with the potential configurations. The updated configuration specifies an additional number of virtual machines associated with hosting the codec process. The computer system launches the additional number of virtual machines.

Growing community of inventors

San Jose, CA, United States of America

Haoliang Wang