摘要:
Techniques are disclosed to enable generation of a high-resolution image from any generic low-resolution image. In one described implementation, a method includes extracting, at a training phase, a plurality of primal sketch priors from training data. At a synthesis phase, the plurality of primal sketch priors are utilized to improve a low-resolution image by replacing one or more low-frequency primitives extracted from the low-resolution image with corresponding ones of the plurality of primal sketch priors.
摘要:
Embodiments related to the removal of blur from an image are disclosed. One disclosed embodiment provides a method of performing an iterative non-blind deconvolution of a blurred image to form an updated image. The method comprises downsampling the blurred image to form a blurred image pyramid comprising images of two or more different resolution scales, downsampling a blur kernel to form a blur kernel pyramid comprising kernels of two or more different sizes, and deconvoluting a selected image in the blurred image pyramid according to a Richardson-Lucy deconvolution process in which a bilateral range/spatial filter is employed.
摘要:
The alignment of a sharp image of a subject and a blurred image of the same subject is disclosed. For example, one disclosed embodiment provides a method of determining a series of trial images. The method comprises applying a corresponding series of coordinate transforms to the sharp image, the series of coordinate transforms differing with respect to one or more of a rotational operation and a scaling operation. The method further comprises computing a series blur kernels corresponding to the series of trial images, each blur kernel mapping a trial image from the series of trial images to the blurred image. The method further includes locating a sparsest blur kernel in the series of blur kernels, and identifying one or more of the rotational operation and the scaling operation of the coordinate transform mapping the trial image corresponding to the sparsest blur kernel to the blurred image.
摘要:
Described is a technology by which a low-resolution image is processed into a high-resolution image, including by performing processing in the gradient domain. A gradient profile corresponding to the lower-resolution image is transform into a sharpened image gradient. A high-resolution gradient profile is estimated from a low-resolution gradient profile, e.g., by multiplying the low-resolution gradient profile by a transform ratio that is based upon learned shape parameters, learned sharpness values and a curve distance to an edge pixel along the gradient profile. The transform ratio is used to transform a low-resolution gradient field to a high-resolution gradient field. Reconstructing the higher-resolution image is performed by using the high-resolution gradient field as a gradient domain constraint, e.g., in along with a reconstruction constraint obtained from image domain data. An energy function is minimized by enforcing the gradient domain constraint and the reconstruction constraint, e.g., by performing a gradient descent algorithm.
摘要:
Image completion with structure propagation is described. In one aspect, synthesized patches for an unknown region in an input image are automatically generated. The synthesized patches are generated from a known region in the input image based on information from one or more curves. The one or more curves were generated to provide missing structure to the unknown region. Structure is propagated to the unknown region with the synthesized patches.
摘要:
A method for creating an optimized gradient mesh of a vector-based image from a raster-based image. In one implementation, a set of boundaries for an object on a raster-based image may be received. An initial gradient mesh of the object may be created. A residual energy between the object on the raster-based image and a rendered initial gradient mesh may be minimized to generate an optimized gradient mesh.
摘要:
Techniques are disclosed to enable generation of a high-resolution image from any generic low-resolution image. In one described implementation, a method includes extracting, at a training phase, a plurality of primal sketch priors from training data. At a synthesis phase, the plurality of primal sketch priors are utilized to improve a low-resolution image by replacing one or more low-frequency primitives extracted from the low-resolution image with corresponding ones of the plurality of primal sketch priors.
摘要:
Techniques are disclosed to improve quality of images that may be blurred or underexposed (e.g., because of camera shake, taken in dim lighting conditions, or taken of high action scenes). The techniques may be implemented in a digital camera, digital video camera, or a digital camera capable of capturing video. In one described implementation, a digital camera includes an image sensor, a storage device, and a processing unit. The image sensor captures two images from a same scene which are stored on the storage device. The processing unit enhances the captured images with luminance correction.
摘要:
Some implementations provide techniques and arrangements to address intrapersonal variations encountered during facial recognition. For example, some implementations transform at least a portion of an image from a first intrapersonal condition to a second intrapersonal condition to enable more accurate comparison with another image. Some implementations may determine a pose category of an input image and may modify at least a portion of the input image to a different pose category of another image for comparing the input image with the other image. Further, some implementations provide for compression of data representing at least a portion of the input image to decrease the dimensionality of the data.
摘要:
Some implementations provide techniques and arrangements to address intrapersonal variations encountered during facial recognition. For example, some implementations employ an identity data set having a plurality of images representing different intrapersonal settings. A predictive model may associate one or more input images with one or more images in the identity data set. Some implementations may use an appearance-prediction approach to compare two images by predicting an appearance of at least one of the images under an intrapersonal setting of the other image. Further, some implementations may utilize a likelihood-prediction approach for comparing images that generates a classifier for an input image based on an association of an input image with the identity data set.