Microsoft Technology Licensing, LLC

Sebastian Nowozin

Amit Adam

Pushmeet Kohli

Shai Mazor

Omer Yair

Jamie Daniel Joseph Shotton

Marc Manuel Johannes Brockschmidt

Alexander Lloyd Gaunt

Daniel Stefan Tarlow

Ryota Tomioka

Cecily Peregrine Borgatti Morrison

Daniel Coelho De Castro

Matej Balog

Tom Ellis

Diane Bouchacourt

Shahram Izadi

David Kim

Otmar Hilliges

David G Molyneaux

Carsten Curt Eckard Rother

Michael Schober

Christoph Dann

Stefan Johannes Josef Holzer

An image processing system is described which has a memory holding at least one image depicting at least one person previously unseen by the image processing system. The system has a trained probabilistic model which describes a relationship between image features, context, identities and a plurality of names of people, wherein at least one of the identities identifies a person depicted in the image without an associated name in the plurality of names. The system has a feature extractor which extracts features from the image, and a processor which predicts an identity of the person depicted in the image using the extracted features and the probabilistic model.

Image processing for person recognition

A computer program predictor is described which has a processor configured to access a program attribute predictor; and a memory storing a search component configured to search a space of possible programs, to find a program which, given an input data instance and an output data instance, will compute the output data instance from the input data instance, the search being guided by attributes predicted by the attribute predictor given the input data instance and the output data instance.

Program predictor

A data compression apparatus is described which has an encoder configured to receive an input data item and to compress the data item into an encoding comprising a plurality of numerical values. The numerical values are grouped at least according to whether they relate to content of the input data item or style of the input data item. The encoder has been trained using a plurality of groups of training data items grouped according to the content and where training data items within individual ones of the groups vary with respect to the style. The encoder has been trained using a training objective which takes into account the groups.

Data compression system

A depth detection apparatus is described which has a memory storing raw time-of-flight sensor data received from a time-of-flight sensor. The depth detection apparatus also has a trained machine learning component having been trained using training data pairs. A training data pair comprises at least one simulated raw time-of-flight sensor data value and a corresponding simulated ground truth depth value. The trained machine learning component is configured to compute in a single stage, for an item of the stored raw time-of-flight sensor data, a depth value of a surface depicted by the item, by pushing the item through the trained machine learning component.

Depth from time-of-flight using machine learning

A depth detection apparatus is described which has a memory and a computation logic. The memory stores frames of raw time-of-flight sensor data received from a time-of-flight sensor, the frames having been captured by a time-of-flight camera in the presence of motion such that different ones of the frames were captured using different locations of the camera and/or with different locations of an object in a scene depicted in the frames. The computation logic has functionality to compute a plurality of depth maps from the stream of frames, whereby each frame of raw time-of-flight sensor data contributes to more than one depth map.

Temporal time-of-flight

Examples of time-of-flight ('TOF') simulation of multipath light phenomena are described. For example, in addition to recording light intensity for a pixel during rendering, a graphics tool records the lengths (or times) and segment counts for light paths arriving at the pixel. Such multipath information can provide a characterization of the temporal light density of light that arrives at the pixel in response to one or more pulses of light. The graphics tool can use stratification and/or priority sampling to reduce variance in recorded light path samples. Realistic, physically-accurate simulation of multipath light phenomena can, in turn, help calibrate a TOF camera so that it more accurately estimates the depths of real world objects observed using the TOF camera. Various ways to improve the process of inferring imaging conditions such as depth, reflectivity, and ambient light based on images captured using a TOF camera are also described.

Time-of-flight simulation of multipath light phenomena

A gesture detection and recognition technique is described. In one example, a sequence of data items relating to the motion of a gesturing user is received. A selected set of data items from the sequence are tested against pre-learned threshold values, to determine a probability of the sequence representing a certain gesture. If the probability is greater than a predetermined value, then the gesture is detected, and an action taken. In examples, the tests are performed by a trained decision tree classifier. In another example, the sequence of data items can be compared to pre-learned templates, and the similarity between them determined. If the similarity for a template exceeds a threshold, a likelihood value associated with a future time for a gesture associated with that template is updated. Then, when the future time is reached, the gesture is detected if the likelihood value is greater than a predefined value.

Gesture detection and recognition

Learning image processing tasks from scene reconstructions is described where the tasks may include but are not limited to: image de-noising, image in-painting, optical flow detection, interest point detection. In various embodiments training data is generated from a 2 or higher dimensional reconstruction of a scene and from empirical images of the same scene. In an example a machine learning system learns at least one parameter of a function for performing the image processing task by using the training data. In an example, the machine learning system comprises a random decision forest. In an example, the scene reconstruction is obtained by moving an image capture apparatus in an environment where the image capture apparatus has an associated dense reconstruction and camera tracking system.

Learning image processing tasks from scene reconstructions

Classification algorithm optimization is described. In an example, a classification algorithm is optimized by calculating an evaluation sequence for a set of weighted feature functions that orders the feature functions in accordance with a measure of influence on the classification algorithm. Classification thresholds are determined for each step of the evaluation sequence, which indicate whether a classification decision can be made early and the classification algorithm terminated without evaluating further feature functions. In another example, a classifier applies the weighted feature functions to previously unseen data in the order of the evaluation sequence and determines a cumulative value at each step. The cumulative value is compared to the classification thresholds at each step to determine whether a classification decision can be made early without evaluating further feature functions.

Growing community of inventors

Cambridge, United Kingdom

Sebastian Nowozin