Abstract: Methods and apparatus to control appearance of views in free viewpoint media are disclosed. An apparatus includes at least one memory; instructions; and processor circuitry to execute the instructions to: determine a first point in three-dimensional space relative to a plurality of real-world cameras, the first point corresponding to a region of interest in a real-world scene to be captured by the real-world cameras; determine, independent of the first point, a second point in the three-dimensional space; and determine parameters for a virtual camera based on both the first point and the second point, the parameters to enable generation of a virtual image from a perspective of the virtual camera based on a modification of a real-world image captured by one of the real-world cameras.

Abstract: An example apparatus enabling a dual fisheye model and calibration is described. The apparatus includes at least one memory; and at least one processor to execute instructions to: generate a first set of coefficients for an inverse distortion polynomial, the inverse distortion polynomial indicative of radial distortion of an image captured by a camera; generate a second set of coefficients for an alternative distortion polynomial, the alternative distortion polynomial to enable identification of a first point in the image corresponding to a second point in a three-dimensional space represented by the image; and determine a location of the camera within the three-dimensional space based on at least one of the inverse distortion polynomial or the alternative distortion polynomial.

Abstract: An example apparatus enabling a dual fisheye model and calibration is described. The apparatus includes at least one memory; and at least one processor to execute instructions to: generate a first set of coefficients for an inverse distortion polynomial, the inverse distortion polynomial indicative of radial distortion of an image captured by a camera; generate a second set of coefficients for an alternative distortion polynomial, the alternative distortion polynomial to enable identification of a first point in the image corresponding to a second point in a three-dimensional space represented by the image; and determine a location of the camera within the three-dimensional space based on at least one of the inverse distortion polynomial or the alternative distortion polynomial.

Abstract: A method and system of image processing of omnidirectional images with a viewpoint shift.

Abstract: An example system enabling a dual fisheye model and calibration is described. The system includes a calibration module that simultaneously generates a first set of coefficients of an inverse distortion polynomial f(?) representing radial distortion and a second set of coefficients of an alternative distortion polynomial g(?). Further, the present techniques may also calibrate intrinsic and extrinsic parameters.

Abstract: An example system for identification of three-dimensional points includes a receiver to receive coordinates of a two-dimensional point in an image, and a set of calibration parameters. The system also includes a 2D-to-3D point identifier to identify a three-dimensional point in a scene corresponding to the 2D point using the calibration parameters and a non-central camera model including an axial viewpoint shift function comprising a function of a radius of a projected point in an ideal image plane.

Abstract: Deblurring a blurry image (14) includes the steps of (i) computing a spatial mask (256); (ii) computing a modified blurry image (264) using the blurry image (14) and the spatial mask (256); and (iii) computing a latent sharp image (16) using the modified blurry image (264) and a point spread function (260). Additionally, the image (714) can be analyzed to identify areas of the image (714) that are suitable for point spread function estimation. Moreover, a region point spread function (1630) can be analyzed to classify the point spread function(s) as representing (i) motion blur, (ii) defocus blur, or (iii) mixed motion blur and defocus blur. A point spread function (2670) can also be estimated.

Abstract: A method for deblurring a blurry image (400) includes the steps of: performing a first phase of deconvolution (202) with a first phase regularization spatial mask (300) to reconstruct the main edges and generate a first phase latent sharp image (404) having reconstructed main edges; and performing a second phase of deconvolution (204) with a second phase regularization spatial mask (304) to reconstruct the texture and generate a second phase latent sharp image (406). The second phase regularization spatial mask (304) can be different from the first phase regularization spatial mask (300).

Abstract: An example system enabling a dual fisheye model and calibration is described. The system includes a calibration module that simultaneously generates a first set of coefficients of an inverse distortion polynomial f(?) representing radial distortion and a second set of coefficients of an alternative distortion polynomial g(?). Further, the present techniques may also calibrate intrinsic and extrinsic parameters.

Abstract: A method for estimating an optics point spread function (518) of a lens assembly (20) includes (i) providing a test chart (14); (ii) providing a capturing system (22); (iii) capturing a test chart image (316) of the test chart (14) with the capturing system (22) using the lens assembly (20) to focus light onto the capturing system (22); (iv) selecting an image area (490) from the test chart image (316); (v) dividing the image area (490) into a plurality of area blocks (494); and (vii) estimating an area point spread function (518) of the image area (490) using a PSF cost function that sums the fidelity terms of at least two of the area blocks (494).

Abstract: A method for deblurring a blurry image (400) includes the steps of: performing a first phase of deconvolution (202) with a first phase regularization spatial mask (300) to reconstruct the main edges and generate a first phase latent sharp image (404) having reconstructed main edges; and performing a second phase of deconvolution (204) with a second phase regularization spatial mask (304) to reconstruct the texture and generate a second phase latent sharp image (406). The second phase regularization spatial mask (304) can be different from the first phase regularization spatial mask (300).

Abstract: A method for estimating a latent sharp image (15) for a blurry image (14) includes estimating the latent sharp image (15) with a control system (20) that utilizes a latent sharp image estimation cost function having a regularization term (538) that has a linear first section (540) and a linear second section (542) to characterize the pixels (14A) and adjust the pixels (14A) to create the latent sharp image (15) with the adjusted pixels (15A). The first section (540) has a first slope and the second section (542) has a second slope that is different from the first slope. Further, the first section (540) is connected to the second section (542) at a section knot (544).

Abstract: A method for deblurring a blurry image (400) includes the steps of: performing a first phase of deconvolution (202) with a first phase regularization spatial mask (300) to reconstruct the main edges and generate a first phase latent sharp image (404) having reconstructed main edges; and performing a second phase of deconvolution (204) with a second phase regularization spatial mask (304) to reconstruct the texture and generate a second phase latent sharp image (406). The second phase regularization spatial mask (304) can be different from the first phase regularization spatial mask (300).

Abstract: Deblurring a blurry image (14) includes the steps of (i) computing a spatial mask (256); (ii) computing a modified blurry image (264) using the blurry image (14) and the spatial mask (256); and (iii) computing a latent sharp image (16) using the modified blurry image (264) and a point spread function (260). Additionally, the image (714) to can be analyzed to identify areas of the image (714) that are suitable for point spread function estimation. Moreover, a region point spread function (1630) can be analyzed to classify the point spread function(s) as representing (i) motion blur, (ii) defocus blur, or (iii) mixed motion blur and defocus blur.

Abstract: Deblurring a blurry image (14) includes the steps of (i) computing a spatial mask (256); (ii) computing a modified blurry image (264) using the blurry image (14) and the spatial mask (256); and (iii) computing a latent sharp image (16) using the modified blurry image (264) and a point spread function (260). Additionally, the image (714) to can be analyzed to identify areas of the image (714) that are suitable for point spread function estimation. Moreover, a region point spread function (1630) can be analyzed to classify the point spread function(s) as representing (i) motion blur, (ii) defocus blur, or (iii) mixed motion blur and defocus blur. A point spread function (2670) can also be estimated.

Abstract: A group point spread function (238) for a blurry image (18) can be determined by dividing the blurry image (18) into a plurality of image regions (232), estimating a region point spread function (234) for at least two of the image regions (232); and utilizing at least two of the region point spread functions (234) to determine the group point spread function (238). The group point spread function (238) can be determined by the decomposition of the estimated region point spread functions (234) into some basis function, and subsequently determining a representative coefficient from the basis functions of the region point spread functions (234) to generate the group point spread function (238).

Abstract: A method for classifying a test image (16) includes the steps of building a classifier (300), and classifying the test image (16) with the classifier (300). After the test image (16) is classified, the test image (16) can be subsequently processed (e.g. deblurred) with improved accuracy. The classifier (300) can classify and distinguish between PSF features associated with motion blurred images, and PSF features associate with defocus blurred images. The classifier (300) can be built using a plurality of training images (304), and extracting one or more training features from each the training images (304). The PSF features can include image moments of the point spread function, and/or geometric features of the point spread function.

Abstract: A method for deblurring a blurry image (400) includes the steps of: performing a first phase of deconvolution (202) with a first phase regularization spatial mask (300) to reconstruct the main edges and generate a first phase latent sharp image (404) having reconstructed main edges; and performing a second phase of deconvolution (204) with a second phase regularization spatial mask (304) to reconstruct the texture and generate a second phase latent sharp image (406). The second phase regularization spatial mask (304) can be different from the first phase Has the Desired Number No Update Regularization Mask regularization spatial mask (300).

Abstract: A method for estimating an optics point spread function (518) of a lens assembly (20) includes (i) providing a test chart (14); (ii) providing a capturing system (22); (iii) capturing a test chart image (316) of the test chart (14) with the capturing system (22) using the lens assembly (20) to focus light onto the capturing system (22); (iv) selecting an image area (490) from the test chart image (316); (v) dividing the image area (490) into a plurality of area blocks (494); and (vii) estimating an area point spread function (518) of the image area (490) using a PSF cost function that sums the fidelity terms of at least two of the area blocks (494).

Abstract: Deblurring a blurry image (14) includes the steps of (i) computing a spatial mask (256); (ii) computing a modified blurry image (264) using the blurry image (14) and the spatial mask (256); and (iii) computing a latent sharp image (16) using the modified blurry image (264) and a point spread function (260). Additionally, the image (714) to can be analyzed to identify areas of the image (714) that are suitable for point spread function estimation. Moreover, a region point spread function (1630) can be analyzed to classify the point spread function(s) as representing (i) motion blur, (ii) defocus blur, or (iii) mixed motion blur and defocus blur.