Abstract: Exemplary embodiments are directed to a system for selective enhancement of skin features in an image. The system includes an interface configured to receive as input an original image, and a processing device in communication with the interface. The processing device is configured to process the original image using a neural network to detect one or more skin imperfections in the original image, generate a neural network mask of the original image for the one or more skin imperfections in the original image, generate one or more source patches based on the original image, and, replace the one or more skin imperfections in the original image with the one or more source patches to generate a patched skin image.

Abstract: Example embodiments are directed to a system of image enhancement. An interface device is configured to receive as input one or more input images. The one or more input images have one or more exposure values. A processing device is configured to execute an exposure value (EV) resampling module to generate one or more resampled images having exposure values different from the one or more exposure values of the one or more input images. The resampled images have a range of exposure values. The processing device is configured to execute a filtering module to filter the resampled images, and output a set of filtered images. The processing device is configured to execute a blending module to sequentially blend the set of filtered images, and output a merged image.

Abstract: Exemplary embodiments are directed to a system for content-aware enhancement of an image. The system includes an interface configured to receive as input an original image, and a processing device in communication with the interface. The processing device is configured to process the original image to detect one or more objects in the original image, generate an in-focus person mask of the original image for one or more in-focus people in the original image, and apply one or more enhancements to areas of the original image excluding the in-focus person mask.

Abstract: Exemplary embodiments are directed to a system for selective enhancement of skin features in an image. The system includes an interface configured to receive as input an original image, and a processing device in communication with the interface. The processing device is configured to process the original image using a neural network to detect one or more skin imperfections in the original image, generate a neural network mask of the original image for the one or more skin imperfections in the original image, generate one or more source patches based on the original image, and, replace the one or more skin imperfections in the original image with the one or more source patches to generate a patched skin image.

Abstract: Exemplary embodiments are directed to a system for selective replacement of an object in an image. The system includes an interface configured to receive as input an original image and a background image, and a processing device in communication with the interface. The processing device is configured to process the original image using a neural network to detect one or more objects in the original image, generate a neural network mask of the original image for the one or more objects in the original image, generate a filtered original image including the original image without the one or more objects, generate a modulated background image including a replacement background based on the neural network mask, and generate a combined image including the filtered original image combined with the modulated background image.

Abstract: Exemplary embodiments are directed to a system for selective replacement of an object in an image. The system includes an interface configured to receive as input an original image and a background image, and a processing device in communication with the interface. The processing device is configured to process the original image using a neural network to detect one or more objects in the original image, generate a neural network mask of the original image for the one or more objects in the original image, generate a filtered original image including the original image without the one or more objects, generate a modulated background image including a replacement background based on the neural network mask, and generate a combined image including the filtered original image combined with the modulated background image.

Abstract: Example embodiments are directed to a system of image enhancement. An interface device is configured to receive as input one or more input images. The one or more input images have one or more exposure values. A processing device is configured to execute an exposure value (EV) resampling module to generate one or more resampled images having exposure values different from the one or more exposure values of the one or more input images. The resampled images have a range of exposure values. The processing device is configured to execute a filtering module to filter the resampled images, and output a set of filtered images. The processing device is configured to execute a blending module to sequentially blend the set of filtered images, and output a merged image.

Abstract: Example embodiments are directed to a system of image enhancement. An interface device is configured to receive as input one or more input images. The one or more input images have one or more exposure values. A processing device is configured to execute an exposure value (EV) resampling module to generate one or more resampled images having exposure values different from the one or more exposure values of the one or more input images. The resampled images have a range of exposure values. The processing device is configured to execute a filtering module to filter the resampled images, and output a set of filtered images. The processing device is configured to execute a blending module to sequentially blend the set of filtered images, and output a merged image.

Abstract: Exemplary embodiments are directed to a system for content-aware enhancement of an image. The system includes an interface configured to receive as input an original image, and a processing device in communication with the interface. The processing device is configured to process the original image to detect one or more objects in the original image, generate an in-focus person mask of the original image for one or more in-focus people in the original image, and apply one or more enhancements to areas of the original image excluding the in-focus person mask.

Abstract: Exemplary embodiments are directed to a system for selective enhancement of skin features in an image. The system includes an interface configured to receive as input an original image, and a processing device in communication with the interface. The processing device is configured to process the original image using a neural network to detect one or more skin imperfections in the original image, generate a neural network mask of the original image for the one or more skin imperfections in the original image, generate one or more source patches based on the original image, and, replace the one or more skin imperfections in the original image with the one or more source patches to generate a patched skin image.

Abstract: Exemplary embodiments are directed to a system for selective replacement of an object in an image. The system includes an interface configured to receive as input an original image and a background image, and a processing device in communication with the interface. The processing device is configured to process the original image using a neural network to detect one or more objects in the original image, generate a neural network mask of the original image for the one or more objects in the original image, generate a filtered original image including the original image without the one or more objects, generate a modulated background image including a replacement background based on the neural network mask, and generate a combined image including the filtered original image combined with the modulated background image.

Abstract: Example embodiments are directed to a system of image enhancement. An interface device is configured to receive as input one or more input images. The one or more input images have one or more exposure values. A processing device is configured to execute an exposure value (EV) resampling module to generate one or more resampled images having exposure values different from the one or more exposure values of the one or more input images. The resampled images have a range of exposure values. The processing device is configured to execute a filtering module to filter the resampled images, and output a set of filtered images. The processing device is configured to execute a blending module to sequentially blend the set of filtered images, and output a merged image.

Abstract: A circuit associated with a power converter, a method of operation thereof and a power converter employing the circuit or the method. The power converter has a primary switching circuit coupled to a tapped primary winding of an isolation transformer and a rectifier coupled to a secondary winding of the isolation transformer. The circuit is coupled across a tapped portion of the tapped primary winding. In one embodiment, the circuit includes: (1) an inductor, configured to reduce current spikes in the primary switching circuit caused by a reverse recovery phenomenon associated with the rectifier and to effect substantially zero voltage switching of a power switch of the primary switching circuit; and (2) a diode, coupled to the inductor via the tapped portion, configured to clamp a voltage across the rectifier. The tapped portion is configured to enable energy from the inductor to be recovered within the power converter.

Abstract: A boost converter, a method of converting power and a power supply incorporating the boost converter or the method.

Abstract: A single stage power converter, a method of processing rectified AC power, and a power supply incorporating the converter or the method. In one embodiment, the converter is couplable via a rectifier to a source of AC power, has a filter capacitor and an isolation transformer with a primary winding, and includes: (1) a significant energy storage device coupled to the primary winding, (2) a first switch, coupled to the primary winding, that conducts intermittently to couple the primary winding to the rectifier to transfer a portion of rectified AC power to a magnetizing inductance of the isolation transformer and (3) a second switch, coupled between the primary winding and the significant energy storage device, that conducts alternately with the first switch, the first and second switches substantially zero-voltage switching and the converter correcting a power factor of the AC power.