Microsoft Technology Licensing, LLC

Charles Lawrence Zitnick, Iii

Richard S Szeliski

Sing Bing Kang

Simon Winder

Matthew Uyttendaele

Nadim Y Abdo

Voicu Anton Albu

Michael F Cohen

Neel Suresh Joshi

Piotr Dollar

Sudipta Narayan Sinha

Simon John Baker

Adam G Kirk

Bryan Kent Ressler

Dennis I Park

Shahram Izadi

Kestutis Patiejunas

Nebojsa Jojic

Andreas Georgiou

David Eraker

Max Alan McMullen

Avronil Bhattacharjee

Richard Lloyd Hughes

Christoph Rhemann

Oliver Arthur Whyte

Krishnan Ramnath

Saswata Mandal

George Randell Dong

Yaron Eshet

Edward Hsiao

Gerhard Florian Schroff

Xiangyang Lan

Jagannatha Koppal

Varsha Hedau

Yong Jae Lee

Seth Hendrickson

Sanjeev J Koppal

Edges are detected in a digital image including a plurality of pixels. For each of the plurality of pixels, a plurality of different edge assessments are made for that pixel. Each different edge assessment considers that pixel in a different position of a different pixel patch. The different edge assessments for each pixel are aggregated.

Digital image edge detection

The subject disclosure is directed towards a high resolution, high frame rate, robust stereo depth system. The system provides depth data in varying conditions based upon stereo matching of images, including actively illuminated IR images in some implementations. A clean IR or RGB image may be captured and used with any other captured images in some implementations. Clean IR images may be obtained by using a notch filter to filter out the active illumination pattern. IR stereo cameras, a projector, broad spectrum IR LEDs and one or more other cameras may be incorporated into a single device, which may also include image processing components to internally compute depth data in the device for subsequent output.

Depth imaging system based on stereo vision and infrared radiation

A stroke processing system (SPS) is described which processes a user's current instance of handwriting with reference to previous instances of handwriting. In one application, the SPS matches a new token input by a user (corresponding to a sequence of stroke samples) with previous tokens that are similar to the new token. The SPS then refines the new token by averaging it with the previous tokens. This improves the appearance of the new token. In another application, the SPS uses the previous tokens to produce a search result. In another application, the SPS uses the previous tokens to perform an auto-completion operation.

Leveraging previous instances of handwriting for handwriting beautification and other applications

The techniques and systems described herein are directed to isolating part-centric motion in a visual scene and stabilizing (e.g., removing) motion in the visual scene that is associated with camera-centric motion and/or object-centric motion. By removing the motion that is associated with the camera-centric motion and/or the object-centric motion, the techniques are able to focus motion feature extraction mechanisms (e.g., temporal differencing) on the isolated part-centric motion. The extracted motion features may then be used to recognize and/or detect the particular type of object and/or estimate a pose or position of a particular type of object.

Motion stabilization and detection of articulated objects

Systems, methods and computer-readable storage media are disclosed for accelerating bitmap remoting by extracting non-grid tiles from source bitmaps. A server takes a source image, identifies possibly repetitive features, and tiles the image. For each tile that contains part of a possibly repetitive feature, the server replaces that part with the dominant color of the tile. The system then sends to a client a combination of new tiles and features, and indications to tiles and features that the client has previously received and stored, along with an indication of how to recreate the image based on the tiles and features.

Accelerating bitmap remoting by identifying and extracting 2D patterns from source bitmaps

Described is a user interface that displays a representation of a stereo scene, and includes interactive mechanisms for changing parameter values that determine the perceived appearance of that scene. The scene is modeled as if viewed from above, including a representation of a viewer's eyes, a representation of a viewing screen, and an indication simulating what each of the viewer eyes perceives on the viewing screen. Variable parameters may include a vergence parameter, a dolly parameter, a field-of-view parameter, an interocular parameter and a proscenium arch parameter.

Viewer-centric user interface for stereoscopic cinema

A mobile device having the capability of performing real-time location recognition with assistance from a server is provided. The approximate geophysical location of the mobile device is uploaded to the server. Based on the mobile device's approximate geophysical location, the server responds by sending the mobile device a message comprising a classifier and a set of feature descriptors. This can occur before an image is captured for visual querying. The classifier and feature descriptors are computed during an offline training stage using techniques to minimize computation at query time. The classifier and feature descriptors are used to perform visual recognition in real-time by performing the classification on the mobile device itself.

Location-aided recognition

The claimed subject matter provides for systems and/or methods for identification of instances of an object of interest in 2D images by creating a database of 3D curve models of each desired instance and comparing an image of an object of interest against such 3D curve models of instances. The present application describes identifying and verifying the make and model of a car from a possibly single image&#x2014;after the models have been populated with training data of test images of many makes and models of cars. In one embodiment, an identification system may be constructed by generating a 3D curve model by back-projecting edge points onto a visual hull reconstruction from silhouettes of an instance. The system and methods employ chamfer distance and orientation distance provides reasonable verification performance, as well as an appearance model for the taillights of the car to increase the robustness of the system.

Object identification using 3-D curve matching

Methods and systems for generating a depth map are provided. The method includes projecting an infrared (IR) dot pattern onto a scene. The method also includes capturing stereo images from each of two or more synchronized IR cameras, detecting a number of dots within the stereo images, computing a number of feature descriptors for the dots in the stereo images, and computing a disparity map between the stereo images. The method further includes generating a depth map for the scene using the disparity map.

Generating a depth map

Architecture that guides the freeform drawing of objects by a user to enable the user to produce improved drawings without significant training. As the user draws, the architecture dynamically updates a relevant shadow image proximate (e.g., underlying) the user's strokes. The strokes overlay an evolving shadow image, which shadow image is suggestive of object contours that guide the user during the drawing process. Relevant edge images selected from a large database are automatically blended to construct the shadow image. As the user draws, the strokes are dynamically analyzed using an encoding of overlapping windows for fast matching with the database of images. A top ranked set of matching database edge images are aligned to the drawing, a set of spatially varying weights blend the edge images into the shadow image, and a scoring technique is employed to select the optimum shadow image for display.

Realtime user guidance for freehand drawing

A content-based image retrieval technique for sharing image information between images. In the present image information sharing technique digital photographs containing relevant comments and links to web pages are supplied by a set of authors. A user of the image information sharing technique takes a digital picture of something that interests them, such as, for example, a poster, a product, a painting, and uploads it to an image information sharing server. The image information sharing technique then matches the photo to an image in an image information sharing database. The comments and web links associated with the matched photo are subsequently sent to the user.

Information sharing between images

Video signatures are generated when a small change in video information between consecutive frames N&#x2212;1 and N is followed by a large change in video information between consecutive frames N and N+1. Information from frames N and/or N+1 is used to form a video signature.

Video signature

Described are techniques for image deconvolution to deblur an image given a blur kernel. Localized color statistics derived from the image to be deblurred serve as a prior constraint during deconvolution. A pixel's color is formulated as a linear combination of the two most prevalent colors within a neighborhood of the pixel. This may be repeated for many or all pixels in an image. The linear combinations of the pixels serve as a two-color prior for deconvolving the blurred image. The two-color prior is responsive to the content of the image and it may decouple edge sharpness from edge strength.

Image deconvolution using color priors

A process for compressing and decompressing non-keyframes in sequential sets of contemporaneous video frames making up multiple video streams where the video frames in a set depict substantially the same scene from different viewpoints. Each set of contemporaneous video frames has a plurality frames designated as keyframes with the remaining being non-keyframes. In one embodiment, the non-keyframes are compressed using a multi-directional spatial prediction technique. In another embodiment, the non-keyframes of each set of contemporaneous video frames are compressed using a combined chaining and spatial prediction compression technique. The spatial prediction compression technique employed can be a single direction technique where just one reference frame, and so one chain, is used to predict each non-keyframe, or it can be a multi-directional technique where two or more reference frames, and so chains, are used to predict each non-keyframe.

Growing community of inventors

Seattle, WA, United States of America

Charles Lawrence Zitnick, Iii