Patent application number | Description | Published |
20100053347 | Content-Aware Video Stabilization - In one embodiment, a method comprises receiving a source video sequence; determining a stabilized camera path to which the source video sequence is to be stabilized; and generating a stabilized video sequence, wherein each frame of the stabilized video sequence is generated as a content-aware warp of a corresponding frame in the input sequence. | 03-04-2010 |
20130044186 | Plane-based Self-Calibration for Structure from Motion - Robust techniques for self-calibration of a moving camera observing a planar scene. Plane-based self-calibration techniques may take as input the homographies between images estimated from point correspondences and provide an estimate of the focal lengths of all the cameras. A plane-based self-calibration technique may be based on the enumeration of the inherently bounded space of the focal lengths. Each sample of the search space defines a plane in the 3D space and in turn produces a tentative Euclidean reconstruction of all the cameras that is then scored. The sample with the best score is chosen and the final focal lengths and camera motions are computed. Variations on this technique handle both constant focal length cases and varying focal length cases. | 02-21-2013 |
20130044913 | Plane Detection and Tracking for Structure from Motion - Plane detection and tracking algorithms are described that may take point trajectories as input and provide as output a set of inter-image homographies. The inter-image homographies may, for example, be used to generate estimates for 3D camera motion, camera intrinsic parameters, and plane normals using a plane-based self-calibration algorithm. A plane detection and tracking algorithm may obtain a set of point trajectories for a set of images (e.g., a video sequence, or a set of still photographs). A 2D plane may be detected from the trajectories, and trajectories that follow the 2D plane through the images may be identified. The identified trajectories may be used to compute a set of inter-image homographies for the images as output. | 02-21-2013 |
20130071040 | High-Quality Upscaling of an Image Sequence - A method, system, and computer-readable storage medium are disclosed for upscaling an image sequence. An upsampled frame is generated based on an original frame in an original image sequence comprising a plurality of frames. A smoothed image sequence is generated based on the original image sequence. A plurality of patches are determined in the upsampled frame. Each patch comprises a subset of image data in the upsampled frame. Locations of a plurality of corresponding patches are determined in a neighboring set of the plurality of frames in the smoothed image sequence. A plurality of high-frequency patches are generated. Each high-frequency patch is based on image data at the locations of the corresponding patches in the original image sequence. The plurality of high-frequency patches are added to the upsampled frame to generate a high-quality upscaled frame. | 03-21-2013 |
20130071041 | High-Quality Denoising of an Image Sequence - A method, system, and computer-readable storage medium are disclosed for denoising an image sequence. A first patch is determined in a first frame in an image sequence comprising a plurality of frames. The first patch comprises a subset of image data in the first frame. Locations of a plurality of corresponding patches are determined in a neighboring set of the plurality of frames. One or more neighboring related patches are determined for each of the plurality of corresponding patches in a same frame as the respective one of the corresponding patches. A denoised first patch is generated by averaging image data in the one or more neighboring related patches in the neighboring set of the plurality of frames. | 03-21-2013 |
20130077890 | Metadata-Driven Method and Apparatus for Constraining Solution Space in Image Processing Techniques - Methods and apparatus for constraining solution space in image processing techniques may use the metadata for a set of images to constrain an image processing solution to a smaller solution space. In one embodiment, a process may require N parameters for processing an image. A determination may be made from metadata that multiple images were captured with the same camera/lens and with the same settings. A set of values may be estimated for the N parameters from data in one or more of the images. The process may then be applied to each of images using the set of values. In one embodiment, a value for a parameter of a process may be estimated for an image. If the estimated value deviates substantially from a value for the parameter in the metadata, the metadata value is used in the process instead of the estimated value. | 03-28-2013 |
20130089262 | Metadata-Driven Method and Apparatus for Constraining Solution Space in Image Processing Techniques - Methods and apparatus for constraining solution space in image processing techniques may use the metadata for a set of images to constrain an image processing solution to a smaller solution space. In one embodiment, a process may require N parameters for processing an image. A determination may be made from metadata that multiple images were captured with the same camera/lens and with the same settings. A set of values may be estimated for the N parameters from data in one or more of the images. The process may then be applied to each of images using the set of values. In one embodiment, a value for a parameter of a process may be estimated for an image. If the estimated value deviates substantially from a value for the parameter in the metadata, the metadata value is used in the process instead of the estimated value. | 04-11-2013 |
20130120375 | SELECTIVELY DISPLAYING SURFACES OF AN OBJECT MODEL - Techniques for selectively displaying surfaces of an object model to a user are described. In one embodiment, a computer-implemented method may include, for a given one of a plurality of surfaces included in an object model that is representative of a physical object, determining a normal vector of the given surface. The method may also include determining an angle between the normal vector of the given surface and a current viewing direction of the model. The method may further include displaying the object model to a user without displaying the given surface to the user, dependent upon determining that the angle between the normal vector and the current viewing direction is greater than a threshold value. | 05-16-2013 |
20130120600 | Methods and Apparatus for Subspace Video Stabilization - Methods, apparatus, and computer-readable storage media for subspace video stabilization. A subspace video stabilization technique may provide a robust and efficient approach to video stabilization that achieves high-quality camera motion for a wide range of videos. The technique may transform a set of input two-dimensional (2D) motion trajectories so that they are both smooth and resemble visually plausible views of the imaged scene; this may be achieved by enforcing subspace constraints on feature trajectories while smoothing them. The technique may assemble tracked features in the video into a trajectory matrix, factor the trajectory matrix into two low-rank matrices, and perform filtering or curve fitting in a low-dimensional linear space. The technique may employ a moving factorization technique that is both efficient and streamable. | 05-16-2013 |
20130121525 | Method and Apparatus for Determining Sensor Format Factors from Image Metadata - Method and apparatus for determining sensor format factors from image metadata in which one of multiple techniques is applied to determine a sensor format factor for a camera from information in the metadata. Information from the metadata may be used to identify which of the multiple techniques to use. For example, the camera make and model may be used to determine a particular technique to use. As another example, the presence or absence of particular attributes or values for particular attributes may be used in determining a particular technique. In one embodiment, a profile database may be searched according to information in the metadata to determine if a sensor format factor for the camera is in the database. If the sensor format factor for the camera is not in the database, other information in the metadata may be examined to determine a particular technique from among the plurality of techniques. | 05-16-2013 |
20130121558 | Point Selection in Bundle Adjustment - In an embodiment, a method comprises receiving a set of three dimensional ( | 05-16-2013 |
20130124147 | Random Sample Consensus for Groups of Data - In one embodiment, a computer accessible storage medium stores a plurality of instructions which, when executed: group a set of reconstructed three dimensional (3D) points derived from image data into a plurality of groups based on one or more attributes of the 3D points; select one or more groups from the plurality of groups; and sample data from the selected groups, wherein the sampled data is input to a consensus estimator to generate a model that describes a 3D model of a scene captured by the image data. Other embodiments may bias sampling into a consensus estimator for any data set, based on relative quality of the data set. | 05-16-2013 |
20130124148 | System and Method for Generating Editable Constraints for Image-based Models - An image-based 3D model of an object may be generated from multiple images of the object captured from different viewpoints. 3D constraints which define the shape of the model may be generated from image data and camera parameters (intrinsic and extrinsic) of the images and from user-specified constraints. A user may specify constraints by outlining, on images of the object, features which define the shape of an object. An approximation of the object's 3D surface may be generated from depth maps computed from the images. The 3D constraints and surface approximation may be converted into a polygonal mesh representation, from which a visual display of the model may be reconstructed. The model may be displayed with a set of editable constraints which a user may manipulate to change the shape of the 3D model. The model may be stored as, and reconstructed from, the set of 3D constraints. | 05-16-2013 |
20130124159 | Methods and Apparatus for Retargeting and Prioritized Interpolation of Lens Profiles - Methods and apparatus for retargeting and prioritized interpolation of lens profiles. A lens profile file may include a set of lens sub-profiles. The camera body and/or settings described in the file may not exactly match that of camera body and/or settings used to capture a target image. A sub-profile processing module may perform a prioritized sub-profile sorting and interpolation method to generate an interpolated sub-profile that may be applied to the target image to correct aberrations including, but not limited to, geometric distortion, lateral chromatic aberration, and vignette. Thus, models generated for a reference camera at a variety of settings may be applied to a target image captured with the same type of lens but with a different camera and/or with different settings that are not exactly modeled in the lens profile file. | 05-16-2013 |
20130124471 | Metadata-Driven Method and Apparatus for Multi-Image Processing - Methods and apparatus for processing collections of images are described in which metadata from a set of images may be used in directing a multi-image processing workflow. One or more output images may be rendered from a set of input images, with each output image being some combination of two or more of the input images. To render an output image, a workflow including one or more processing steps may be applied to the images. Metadata may be used in directing and performing the workflow. For example, metadata may be used in determining a particular workflow for a set of images. As another example, metadata may be used to sort a collection of images into multiple categories for automated workflow processing. As yet another example, metadata may be used to retrieve information stored in a profile database that may be used in processing the images. | 05-16-2013 |
20130127847 | System and Method for Interactive Image-based Modeling of Curved Surfaces Using Single-view and Multi-view Feature Curves - Various embodiments of an interactive system and methods for generating an image-based 3D model of an object from multiple images captured from different viewpoints of the object are described. A user may identify feature curves for the object by outlining the feature curves on a display of the images. The user may outline a feature curve in multiple images which depict the feature curve from different viewpoints. 3D shape constraints for the model may be generated dependent on the identified feature curves and camera parameters for the images. The user may also outline multiple single-view feature curves, such as silhouette curves, in single images. A 3D surface approximation for the model may be generated from the single-view feature curves. The 3D shape constraints and the 3D surface approximation may be used to generate a polygonal mesh which represents the surface of the 3D model of the object. | 05-23-2013 |
20130128062 | Methods and Apparatus for Robust Video Stabilization - Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique. | 05-23-2013 |
20130128063 | Methods and Apparatus for Robust Video Stabilization - Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique. | 05-23-2013 |
20130128064 | Methods and Apparatus for Robust Video Stabilization - Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique. | 05-23-2013 |
20130128065 | Methods and Apparatus for Robust Video Stabilization - Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique. | 05-23-2013 |
20130128066 | Methods and Apparatus for Robust Video Stabilization - Methods and apparatus for robust video stabilization. A video stabilization technique applies a feature tracking technique to an input video sequence to generate feature trajectories. The technique applies a video partitioning technique to segment the input video sequence into factorization windows and transition windows. The technique smoothes the trajectories in each of the windows, in sequence. For factorization windows, a subspace-based optimization technique may be used. For transition windows, a direct track optimization technique that uses a similarity motion model may be used. The technique then determines and applies warping models to the frames in the video sequence. In at least some embodiments, the warping models may include a content-preserving warping model, a homography model, a similarity transform model, and a whole-frame translation model. The warped frames may then be cropped according to a cropping technique. | 05-23-2013 |
20130129154 | Methods and Apparatus for Detecting Poorly Conditioned Points in Bundle Adjustment - Methods and apparatus for detecting and removing poorly conditioned points in bundle adjustment. A detection technique may be used to detect poorly conditioned points during the bundle adjustment process or portion of a feature-based 3D reconstruction pipeline. Once the poorly conditioned points are detected, the technique removes the points from the bundle adjustment process. The technique detects and removes the poorly conditioned points before the optimization is performed, and therefore ensures that the optimization will be successful. | 05-23-2013 |
20130129191 | Methods and Apparatus for Image Rectification for Stereo Display - A set of features in a pair of images is associated to selected cells within a set of cells using a base mesh. Each image of the pair of images is divided using the base mesh to generate the set of cells. The set of features is defined in terms of the selected cells. A stereo image pair is generated by transforming the set of cells with a mesh-based transformation function. A transformation of the set of cells is computed by applying an energy minimization function to the set of cells. A selected transformed mesh and another transformed mesh are generated by applying the transformation of the set of cells to the base mesh. The mesh-based transformation function preserves selected properties of the set of features in the pair of images. | 05-23-2013 |
20130142431 | Metadata Based Alignment of Distorted Images - A method for aligning and unwarping distorted images in which lens profiles for a variety of lens and camera combinations are precomputed. Metadata stored with images is used to automatically determine if a set of component images include an excessive amount of distortion, and if so the metadata is used to determine an appropriate lens profile and initial unwarping function. The initial unwarping function is applied to the coordinates of feature points of the component images to generate substantially rectilinear feature points, which are used to estimate focal lengths, centers, and relative rotations for pairs of the images. A global nonlinear optimization is applied to the initial unwarping function(s) and the relative rotations to generate optimized unwarping functions and rotations for the component images. The optimized unwarping functions and rotations may be used to render a panoramic image. | 06-06-2013 |
20130243351 | Methods and Apparatus for Interfacing Panoramic Image Stitching with Post-Processors - Methods and apparatus for describing a projection model, used by a panoramic image stitching module to generate panoramic images and for communicating the projection model to other processes. A post-processing module may access and use the projection model provided by the panoramic image stitching module to perform one or more post-processing methods on the panoramic image, rather than requiring the user to input the projection model via a user interface or requiring the post-processing module to estimate the projection model according to a mathematical analysis of the panoramic image. | 09-19-2013 |
20130265387 | Opt-Keyframe Reconstruction for Robust Video-Based Structure from Motion - An opt-keyframe reconstruction technique for selecting and reconstructing optimizing keyframes to provide a better reconstruction in a structure from motion (SFM) technique. The technique may, for example, be used in an adaptive reconstruction algorithm implemented by a general SFM technique. This technique may add and reconstruct optimizing frames to a set of keyframes already generated by an initialization technique and by an adaptive technique for iteratively selecting and reconstructing additional keyframes. In addition, the technique may determine and remove outlier points from the projection, and determine and recover inlier points in the projection. Adding the opt-keyframes and inlier points may result in additional, and possibly shorter, point trajectories being included in the reconstruction, thus providing a better reconstruction that may be more suited for later operations that may be applied to the image sequence. | 10-10-2013 |
20130265439 | Robust Video-based Camera Rotation Estimation - A robust system and method for estimating camera rotation in image sequences. A rotation-based reconstruction technique is described that is directed to performing reconstruction for image sequences with a zero or near-zero translation component. The technique may estimate only the rotation component of the camera motion in an image sequence, and may also estimate the camera intrinsic parameters if not known. Input to the technique may include an image sequence, and output may include the camera intrinsic parameters and the rotation parameters for all the images in the sequence. By only estimating a rotation component of camera motion, the assumption is made that the camera is not moving throughout the entire sequence. However, the camera is allowed to rotate and zoom arbitrarily. The technique may support both the case where the camera intrinsic parameters are known and the case where the camera intrinsic parameters are not known. | 10-10-2013 |
20130265443 | Nonlinear Self-Calibration for Structure From Motion (SFM) Techniques - A nonlinear self-calibration technique that may, for example, be used to convert a projective reconstruction to metric (Euclidian) reconstruction. The self-calibration technique may use a nonlinear least squares optimization technique to infer the parameters. N input images and a projective reconstruction for each image may be obtained. At least two sets of initial values may be determined for an equation to be optimized according to the nonlinear optimization technique to generate a metric reconstruction for the set of N images. The equation may then be optimized using each set of initial values according to the nonlinear optimization technique. The result with a smaller cost may be selected. The metric reconstruction is output. The output may include, but is not limited to, focal length, rotation, and translation values for the N images. | 10-10-2013 |
20130266179 | Initialization for Robust Video-Based Structure from Motion - An initialization technique that may, for example, be used in an adaptive reconstruction algorithm implemented by structure from motion (SFM) techniques. The initialization technique computes an initial reconstruction from a subset of frames in an image sequence. The initialization technique may be performed to determine and reconstruct a set of initial keyframes covering a portion of the image sequence according to the point trajectories. In the initialization technique, a set of temporally spaced keyframe candidates is determined and two initial keyframes are selected from the set of keyframe candidates. The two initial keyframes are reconstructed, and then one or more additional keyframes between the two initial keyframes are selected and reconstructed. | 10-10-2013 |
20130266180 | Keyframe Selection for Robust Video-Based Structure from Motion - An adaptive technique is described for iteratively selecting and reconstructing keyframes to fully cover an image sequence that may, for example, be used in an adaptive reconstruction algorithm implemented by a structure from motion (SFM) technique. A next keyframe to process may be determined according to an adaptive keyframe selection technique. The determined keyframe may be reconstructed and added to the current reconstruction. A global optimization may be performed on the current reconstruction. One or more outlier points may be determined and removed from the reconstruction. One or more inlier points may be determined and recovered. If the number of inlier points that were added exceeds a threshold, then global optimization may again be performed. If the current reconstruction is a projective construction, self-calibration may be performed to upgrade the projective reconstruction to a Euclidean reconstruction. | 10-10-2013 |
20130266218 | Detecting and Tracking Point Features with Primary Colors - A feature tracking technique for detecting and tracking feature points with primary colors. An energy value may be computed for each color channel of a feature. If the energy of all the channels is above a threshold, then the feature may be tracked according to a feature tracking method using all channels. Otherwise, if the energy of all of the channels is below the threshold, then the feature is not tracked. If the energy of at least one (but not all) of the channels is below the threshold, then the feature is considered to have primary color, and the feature may be tracked according to the feature tracking method using only the one or more channels with energy above the threshold. The feature tracking techniques may, for example, be used to establish point trajectories in an image sequence for various Structure from Motion (SFM) techniques. | 10-10-2013 |
20130266238 | Algorithm Selection for Structure from Motion - A technique for selecting a particular reconstruction technique to be applied to an image sequence. The technique may analyze an input image sequence and, based on one or more characteristics of the image sequence, select a reconstruction technique as the appropriate technique for the image sequence from among a set of reconstruction techniques. For example, the set may include two or more of a rotation-based reconstruction technique, a plane-based reconstruction technique, and a general 3D reconstruction technique. The selection technique may be combined with the reconstruction techniques to produce a system that takes as input an image sequence or a set of point trajectories, selects an appropriate reconstruction technique, and applies the selected reconstruction technique to generate an estimate of camera motion and camera intrinsic parameters for the image sequence. The technique may be adapted to select among other types of techniques that may be applied to image sequences. | 10-10-2013 |
20140254881 | Statistics of Nearest Neighbor Fields - In embodiments of statistics of nearest neighbor fields, matching patches of a nearest neighbor field can be determined at image grid locations of a first digital image and a second digital image. A motion field can then be determined based on motion data of the matching patches. Predominant motion components of the motion field can be determined based on statistics of the motion data to generate a final motion field. The predominant motion components correspond to a motion of objects as represented by a displacement between the first and second digital images. One of the predominant motion components can then be assigned to each of the matching patches to optimize the final motion field of the matching patches. | 09-11-2014 |
20140254882 | Optical Flow with Nearest Neighbor Field Fusion - In embodiments of optical flow with nearest neighbor field fusion, an initial motion field can be generated based on the apparent motion of objects between digital images, and the initial motion field accounts for small displacements of the object motion. Matching patches of a nearest neighbor field can also be determined for the digital images, where patches of an initial size are compared to determine the matching patches, and the nearest neighbor field accounts for large displacements of the object motion. Additionally, region patch matches can be compared and determined between the digital images, where the region patches are larger than the initial size matching patches. Optimal pixel assignments can then be determined for a fused image representation of the digital images, where the optimal pixel assignments are determined from the initial motion field, the matching patches, and the region patch matches. | 09-11-2014 |
20140254933 | Spatially Coherent Nearest Neighbor Fields - In embodiments of spatially coherent nearest neighbor fields, initial matching patches of a nearest neighbor field can be determined at image grid locations of a first digital image and a second digital image. Spatial coherency can be enforced for each matching patch in the second digital image with reference to respective matching patches in the first digital image based on motion data of neighboring matching patches. A multi-resolution iterative process can then update each spatially coherent matching patch based on overlapping grid regions of the matching patches that are evaluated for matching regions of the first and second digital images. An optimal, spatially coherent matching patch can be selected for each of the image grid locations of the first and second digital images based on iterative interaction to enforce the spatial coherency of each matching patch and the multi-resolution iterative process to update each spatially coherent matching patch. | 09-11-2014 |
20140254943 | Optical Flow Accounting for Image Haze - In embodiments of optical flow accounting for image haze, digital images may include objects that are at least partially obscured by a haze that is visible in the digital images, and an estimate of light that is contributed by the haze in the digital images can be determined The haze can be cleared from the digital images based on the estimate of the light that is contributed by the haze, and clearer digital images can be generated. An optical flow between the clearer digital images can then be computed, and the clearer digital images refined based on the optical flow to further clear the haze from the images in an iterative process to improve visibility of the objects in the digital images. | 09-11-2014 |
20140355899 | VIDEO ENHANCEMENT USING RELATED CONTENT - A method and systems of enhancing a video using a related image are provided. One or more patches are identified in the video, with each patch identifying a region that is present in one of the frames of the video that can be mapped to a similar region in at least one other frame of the video. For each identified patch in the video, a best matching patch in the related image is found. The video is enhanced using the best matching patch in the related image for each identified patch in the video. | 12-04-2014 |
20150030206 | Detecting and Tracking Point Features with Primary Colors - A feature tracking technique for detecting and tracking feature points with primary colors. An energy value may be computed for each color channel of a feature. If the energy of all the channels is above a threshold, then the feature may be tracked according to a feature tracking method using all channels. Otherwise, if the energy of all of the channels is below the threshold, then the feature is not tracked. If the energy of at least one (but not all) of the channels is below the threshold, then the feature is considered to have primary color, and the feature may be tracked according to the feature tracking method using only the one or more channels with energy above the threshold. The feature tracking techniques may, for example, be used to establish point trajectories in an image sequence for various Structure from Motion (SFM) techniques. | 01-29-2015 |
20150030238 | VISUAL PATTERN RECOGNITION IN AN IMAGE - A system may be configured as an image recognition machine that utilizes an image feature representation called local feature embedding (LFE). LFE enables generation of a feature vector that captures salient visual properties of an image to address both the fine-grained aspects and the coarse-grained aspects of recognizing a visual pattern depicted in the image. Configured to utilize image feature vectors with LFE, the system may implement a nearest class mean (NCM) classifier, as well as a scalable recognition algorithm with metric learning and max margin template selection. Accordingly, the system may be updated to accommodate new classes with very little added computational cost. This may have the effect of enabling the system to readily handle open-ended image classification problems. | 01-29-2015 |
20150043806 | AUTOMATIC GEOMETRY AND LIGHTING INFERENCE FOR REALISTIC IMAGE EDITING - Image editing techniques are disclosed that support a number of physically-based image editing tasks, including object insertion and relighting. The techniques can be implemented, for example in an image editing application that is executable on a computing system. In one such embodiment, the editing application is configured to compute a scene from a single image, by automatically estimating dense depth and diffuse reflectance, which respectively form the geometry and surface materials of the scene. Sources of illumination are then inferred, conditioned on the estimated scene geometry and surface materials and without any user input, to form a complete 3D physical scene model corresponding to the image. The scene model may include estimates of the geometry, illumination, and material properties represented in the scene, and various camera parameters. Using this scene model, objects can be readily inserted and composited into the input image with realistic lighting, shadowing, and perspective. | 02-12-2015 |
20150063713 | GENERATING A HIERARCHY OF VISUAL PATTERN CLASSES - A hierarchy machine may be configured as a clustering machine that utilizes local feature embedding to organize visual patterns into nodes that each represent one or more visual patterns. These nodes may be arranged as a hierarchy in which a node may have a parent-child relationship with one or more other nodes. The hierarchy machine may implement a node splitting and tree-learning algorithm that includes hard-splitting of nodes and soft-assignment of nodes to perform error-bounded splitting of nodes into clusters. This may enable the hierarchy machine, which may form all or part of a visual pattern recognition system, to perform large-scale visual pattern recognition, such as font recognition or facial recognition, based on a learned error-bounded tree of visual patterns. | 03-05-2015 |