摘要:
Image deblurring with blurred/noisy image pairs is described. In one implementation, a system combines a blurred image with a corresponding noisy image of the same subject to create a high-quality deblurred image. The blurred/noisy image pair can be acquired by an inexpensive hand-held camera, e.g., in unfavorable low light conditions. An exemplary iterative process uses the blurred image and the noisy image at each step to produce the high-quality image. First, the system estimates the blur kernel of the blurred image using information from both the blurred and noisy images. Then, the system performs residual image deconvolution, which favors suppression of ringing artifacts. Finally, the system applies gain-controlled deconvolution to suppress remaining ringing artifacts in smooth image regions. The system iterates these steps to obtain the final high-quality image.
摘要:
Image resizing for web-based searching is described. In one implementation, a system resizes a user-selected thumbnail image into a larger version of the image that emulates the quality of a large, original image, but without downloading the original image. First, the system extracts resizing parameters when each thumbnail image is created. Then, the system creates a codebook of primitive visual elements extracted from a collection of training images. The primitive visual elements in the codebook provide universal visual parts for reconstructing images. The codebook and a resizing plug-in can be sent once to the user over a background channel. When the user selects a thumbnail image for enlargement, the system resizes the thumbnail image via interpolation and then refines the enlarged image with primitive visual elements from the codebook. The refinement creates an enlarged image that emulates the quality of the large, original image, without downloading the original image.
摘要:
Digital video effects are described. In one aspect, a foreground object in a video stream is identified. The video stream comprises multiple image frames. The foreground object is modified by rendering a 3-dimensional (3-D) visual feature over the foreground object for presentation to a user in a modified video stream. Pose of the foreground object is tracked in 3-D space across respective ones of the image frames to identify when the foreground object changes position in respective ones of the image frames. Based on this pose tracking, aspect ratio of the 3-D visual feature is adaptively modified and rendered over the foreground object in corresponding image frames for presentation to the user in the modified video stream.
摘要:
A method for modeling a time-variant appearance of a material is described. A sample analysis of a material sample is performed, wherein the sample analysis orders surface points of the material sample with respect to weathering from data captured at a single instant in time. An appearance synthesis using the sample analysis is performed, wherein the appearance synthesis generates a time-variant sequence of frames for weathering an object.
摘要:
Described herein is a technology that facilitates efficient large-scale similarity-based retrieval. In several embodiments documents, images, and/or other multimedia files are compactly represented and efficiently indexed to enable robust search using a long-query in a large-scale corpus. As described herein, these techniques include performing decomposition of a file, e.g., a document or document-like representation. The techniques use dimension reduction to obtain three parts, topic-related words (major semantics), document specific words (minor semantics), and background words, representing the major semantics in a feature vector and the minor semantics as keywords. Using the techniques described, file vectors are matched in a topic model and the results ranked based on the keywords.
摘要:
A system and process for broadcast and communication with bi-level or sketch video at extremely low bandwidths is described. Essentially, bi-level and sketch video presents the outlines of the objects in a scene being depicted. Bi-level and sketch video provides a clearer shape, smoother motion, shorter initial latency and cheaper computational cost than do conventional DCT-based video compression methods. This is accomplished by converting each color or gray-scale image frame to bi-level or sketch image frame using adaptive thresholding method, compressing bi-level or sketch image frames into bi-level or sketch video using adaptive context-based arithmetic coding method. Bi-level or sketch video is particularly suitable to such small devices as Pocket PCs and mobile phones that possess small display screen, low bandwidth connection, and light computational power.
摘要:
The present video tracking technique outputs a Maximum A Posterior (MAP) solution for a target object based on two object templates obtained from a start and an end keyframe of a whole state sequence. The technique first minimizes the whole state space of the sequence by generating a sparse set of local two-dimensional modes in each frame of the sequence. The two-dimensional modes are converted into three-dimensional points within a three-dimensional volume. The three-dimensional points are clustered using a spectral clustering technique where each cluster corresponds to a possible trajectory segment of the target object. If there is occlusion in the sequence, occlusion segments are generated so that an optimal trajectory of the target object can be obtained.
摘要:
A flash-based strategy is used to separate foreground information from background information within image information. In this strategy, a first image is taken without the use of flash. A second image is taken of the same subject matter with the use of flash. The foreground information in the flash image is illuminated by the flash to a much greater extent than the background information. Based on this property, the strategy applies processing to extract the foreground information from the background information. The strategy supplements the flash information by also taking into consideration motion information and color information.
摘要:
Systems and methods perform automatic 3D face modeling. In one implementation, a brief video clip of a user's head turning from front to side provides enough input for automatically achieving a model that includes 2D feature matches, 3D head pose, 3D face shape, and facial textures. The video clip of the user may be of poor quality. In a two layer iterative method, the video clip is divided into segments. Flow-based feature estimation and model-based feature refinement are applied recursively to each segment. Then the feature estimation and refinement are iteratively applied across all the segments. The entire modeling method is automatic and the two layer iterative method provides speed and efficiency, especially when sparse bundle adjustment is applied to boost efficiency.
摘要:
An exemplary method includes receiving a trimap for an image that specifies a background region, a foreground region and an unknown region for the image wherein a boundary exists between the foreground region and the unknown region and wherein another boundary exists between the unknown region and the background region, solving a set of Poisson equations having boundary conditions for the two boundaries to provide a matte that distinguishes a foreground region from a background region in the unknown region, and refining the matte by solving a set of Poisson equations for a local unknown region. Various other exemplary technologies are also presented.