Abstract: A method for using a computing device for modifying a lower dynamic range image to a higher dynamic range image is described. According to the method, a lower dynamic range image including a plurality of pixels is analyzed by estimating a dark channel of the plurality of pixels of the lower dynamic range image. A histogram of the dark channel is analyzed by determining the brightest peak and a local minima of the histogram. Using the local minima of the histogram as a threshold for specular highlight determination, a binary mask for specular highlight determination is computed. A final mask is created by multiplying the luminance value of the lower dynamic range image with the binary mask. The final mask is then used to determine the higher dynamic range image. A system for converting a lower dynamic range image to a higher dynamic range image displays the higher dynamic range image on a higher dynamic range display.

Abstract: A system for enhancing an image includes a cadence detection process that detects a cadence of a series of frames, a scene cut detection process that detects a scene cut of the series of frames, and a noise monitoring process that detects noise in the series of frames based upon the cadence detection process. The system also includes a temporal filtering process temporally filtering the series of frames wherein the temporal filtering is modified based upon the scene cut detection process and the noise monitoring process, and a spatial noise reduction process reducing spatial noise in the series of frames wherein the reducing spatial noise is modified based upon the modified temporally filtered frames and the noise monitoring process.

Abstract: A method for using a computing device for modifying a lower dynamic range image to a higher dynamic range image is described. According to the method, a lower dynamic range image including a plurality of pixels is analyzed by estimating a dark channel of the plurality of pixels of the lower dynamic range image. A histogram of the dark channel is analyzed by determining the brightest peak and a local minima of the histogram. Using the local minima of the histogram as a threshold for specular highlight determination, a binary mask for specular highlight determination is computed. A final mask is created by multiplying the luminance value of the lower dynamic range image with the binary mask. The final mask is then used to determine the higher dynamic range image. A system for converting a lower dynamic range image to a higher dynamic range image displays the higher dynamic range image on a higher dynamic range display.

Abstract: A system for determining a high resolution output image that includes receiving a low resolution image and determining an intermediate high resolution image. The system detects semantic features based upon the input image and selects corresponding semantic components from a database based upon the detected semantic features. The first intermediate high resolution image is modified based upon information from the corresponding semantic components to determine the high resolution output image.

Abstract: A method for increasing the resolution of a series of low resolution frames of a low resolution video sequence to a series of high resolution frames of a high resolution video sequence includes receiving the series of low resolution frames of the video sequence. The system determines a first plurality of semantically relevant key points of a first low resolution frame of the series of low resolution frames and determines a second plurality of semantically relevant key points of a second low resolution frame of the series of low resolution frames. The system temporally processes the first plurality of key points based upon the second plurality of key points to determine a more temporally consistent set of key points for the first plurality of key points.

Abstract: Aspects of the present invention are related to systems and methods for estimation of additive noise in an image or in a video sequence. An additive-noise estimate may be computed based on a first significant peak in a histogram of standard-deviation values of patches of an image-channel image associated with an input image.

Abstract: A method for image enhancement may include selecting a plurality of patches of an image and determining at least one dimensionally reduced feature for each of the plurality of patches. The system may further determine a generally closest cluster from a set of clusters for each of the dimensionally reduced features and select a corresponding set of regression coefficients for each of the set of generally closest cluster. The system may also apply the selected set of regression coefficients to a corresponding patch to enhance the image.

Abstract: A method for image enhancement may include selecting a plurality of patches of an image and determining at least one dimensionally reduced feature for each of the plurality of patches. The system may further determine a generally closest cluster from a set of clusters for each of the dimensionally reduced features and select a corresponding set of regression coefficients for each of the set of generally closest cluster. The system may also apply the selected set of regression coefficients to a corresponding patch to enhance the image.

Abstract: A system for determining a high resolution output image that includes receiving a low resolution image and determining an intermediate high resolution image. The system detects semantic features based upon the input image and selects corresponding semantic components from a database based upon the detected semantic features. The first intermediate high resolution image is modified based upon information from the corresponding semantic components to determine the high resolution output image.

Abstract: Aspects of the present invention are related to systems and methods for detection and estimation of mosquito noise in an image or in a video sequence. A mosquito-noise estimate, at a pixel location, may be computed based on an image ring parameter, a statistical value of noise estimates in a first region associated with the pixel location, a maximum activity value in a second region associated with the pixel location and a noise estimate at the pixel location.

Abstract: A system for enhancing an image includes a cadence detection process that detects a cadence of a series of frames, a scene cut detection process that detects a scene cut of the series of frames, and a noise monitoring process that detects noise in the series of frames based upon the cadence detection process. The system also includes a temporal filtering process temporally filtering the series of frames wherein the temporal filtering is modified based upon the scene cut detection process and the noise monitoring process, and a spatial noise reduction process reducing spatial noise in the series of frames wherein the reducing spatial noise is modified based upon the modified temporally filtered frames and the noise monitoring process.

Abstract: A system for enhancing an image includes a cadence detection process that detects a cadence of a series of frames and a scene cut detection process that detects a scene cut of the series of frames. The system also includes a noise monitoring process that detects noise in the series of frames based upon the cadence detection process. The process further includes a temporal filter temporally filtering the series of frames wherein the temporal filtering is modified based upon the scene cut detection process and the noise monitoring process. The system also includes a spatial noise reduction process reducing spatial noise in the series of frames wherein the reducing spatial noise is modified based upon the modified temporally filtered frames and the noise monitoring process.

Abstract: A system for determining a high resolution output image that includes receiving a low resolution image and determining an intermediate high resolution image. The system detects semantic features based upon the input image and selects corresponding semantic components from a database based upon the detected semantic features. The first intermediate high resolution image is modified based upon information from the corresponding semantic components to determine the high resolution output image.

Abstract: A method for increasing the resolution of a series of low resolution frames of a low resolution video sequence to a series of high resolution frames of a high resolution video sequence includes receiving the series of low resolution frames of the video sequence. The system determines a first plurality of semantically relevant key points of a first low resolution frame of the series of low resolution frames and determines a second plurality of semantically relevant key points of a second low resolution frame of the series of low resolution frames. The system temporally processes the first plurality of key points based upon the second plurality of key points to determine a more temporally consistent set of key points for the first plurality of key points.

Abstract: A method for increasing the resolution of a series of low resolution frames of a low resolution video sequence to a series of high resolution frames of a high resolution video sequence includes receiving the series of low resolution frames of the video sequence. The system determines a first plurality of semantically relevant key points of a first low resolution frame of the series of low resolution frames and determines a second plurality of semantically relevant key points of a second low resolution frame of the series of low resolution frames. The system temporally processes the first plurality of key points based upon the second plurality of key points to determine a more temporally consistent set of key points for the first plurality of key points.

Abstract: A method for increasing the resolution of a series of low resolution frames of a low resolution video sequence to a series of high resolution frames of a high resolution video sequence includes receiving the series of low resolution frames of the video sequence. The system determines a first plurality of semantically relevant key points of a first low resolution frame of the series of low resolution frames and determines a second plurality of semantically relevant key points of a second low resolution frame of the series of low resolution frames. The system temporally processes the first plurality of key points based upon the second plurality of key points to determine a more temporally consistent set of key points for the first plurality of key points.

Abstract: Systems and methods for estimation of compression noise in an image or in a video sequence are provided. Difference values in a first direction are computed, and a plurality of statistical feature values for the difference values are computed in association with a plurality of offsets. At least one feature value is computed using the plurality of statistical feature values, and a compression-noise estimate may be determined in accordance with a criterion based on a comparison of the at least on feature value and an associated threshold and an additive noise estimate.

Abstract: A system for determining a high resolution image includes receiving a low resolution image and determining a vector of a patch of the low resolution image based upon a low resolution dictionary. The system includes determining a high resolution patch based upon a high resolution dictionary and the vector and determining the high resolution image based upon the high resolution patch.

Abstract: A system for determining a high resolution output image that includes receiving a low resolution image and determining an intermediate high resolution image. The system detects semantic features based upon the input image and selects corresponding semantic components from a database based upon the detected semantic features. The first intermediate high resolution image is modified based upon information from the corresponding semantic components to determine the high resolution output image.

Abstract: A system for determining a high resolution output image that includes receiving a low resolution image having a first resolution and determining an intermediate high resolution image having a second resolution based upon the low resolution image, where the second resolution is greater than the first resolution. The system determines a set of matches between a patch of the intermediate high resolution image and each of a plurality of degraded high resolution images, then selecting a subset of the set of matches and determining a corresponding reside patch for each of the subset of the set of patches. The system modifies the intermediate high resolution image based upon the corresponding reside patches to determine the high resolution output image.