Samsung Electronics Co., Ltd.

Chenguang Liu

Chang Su

Pradeep Nagesh

William Mandel

Soojung Hyun

McClain C Nelson

Dung Trung Vo

Joonsoo Kim

Yeong-Taeg Kim

Li Tao

Kamal Jnawali

Madhu Athreya

Mcclain C Nelson

A method includes receiving a quantized video having a first maximum luminance level or brightness associated with a mastering display with which the quantized video was mastered. The method also includes de-quantizing the quantized video in order to generate a de-quantized video. The method further includes applying a scene-adaptive tone mapping function to the de-quantized video in order to generate a tone mapped video. In addition, the method includes displaying the tone mapped video on a target display. The tone mapped video has a second maximum luminance level or brightness associated with the target display, and the second maximum luminance level or brightness is less than the first maximum luminance level or brightness.

HDR tone mapping methods with scene adaptive parameterized tone map function

A computer-implemented method includes providing a machine learning network including a global inverse tone mapping (GITM) structure and a local inverse tone mapping (LITM) structure that utilize one or more non-linear basis functions with one or more coefficient functions. The one or more non-linear basis functions learn linearly to facilitate combination with at least one convolution layer for jointly learning the machine learning network. A weighted mask (WM) is provided for reducing one or more visual artifacts, including one or more quantization artifacts in a smooth texture type of region of an output of the machine learning network.

Efficient inverse tone mapping network for standard dynamic range (SDR) to high dynamic range (HDR) conversion on HDR display

One embodiment provides a method comprising receiving an input content, and receiving ambient contextual data indicative of one or more ambient lighting conditions of an environment including a display device. The input content has corresponding metadata that at least partially represents a creative intent indicative of how the input content is intended to be viewed. The method further comprises adaptively correcting the input content based on the ambient contextual data to preserve the creative intent, and providing the corrected input content to the display device for presentation. The adaptively correcting comprises applying automatic white balancing to the input content to correct color tone of the input content.

Content creative intention preservation under various ambient color temperatures

One embodiment provides a computer-implemented method that includes receiving an input image associated with a media content item. The input image includes a luminance-reduced region. One or more luminance values are obtained for a channel obtained using the input image. One or more luminance profiles of a color spectrum are generated using the one or more luminance values. Based on a visual perception effect process that is based on the one or more luminance profiles, colors associated with the luminance-reduced region are enhanced. On a display device, displaying at least the luminance-reduced region with the colors enhanced based on the visual perception effect process based on the one or more luminance profiles.

Perceptual color recovery for luminance reduced displays with burn-in protection

One embodiment provides a computer-implemented method that includes providing a dynamic list structure that stores one or more detected object bounding boxes. Temporal analysis is applied that updates the dynamic list structure with object validation to reduce temporal artifacts. A two-dimensional (2D) buffer is utilized to store a luminance reduction ratio of a whole video frame. The luminance reduction ratio is applied to each pixel in the whole video frame based on the 2D buffer. One or more spatial smoothing filters are applied to the 2D buffer to reduce a likelihood of one or more spatial artifacts occurring in a luminance reduced region.

Self-emitting display (SED) burn-in prevention based on stationary luminance reduction

One embodiment provides a computer-implemented method that includes adaptively adjusting a detection time interval based on stationary region type of one or more stationary regions and a scene length in a video. The method further includes tracking pixels of the one or more stationary regions from a number of previous frames to a current frame in the video in real-time. A minimum and a maximum of max-Red-Green-Blue (MaxRGB) pixel values are extracted from each frame in a scene of the video as minimum and a maximum temporal feature maps for representing pixel variance over time. Segmentation and block matching are applied on the minimum and maximum temporal feature maps to detect the stationary region type.

Detecting stationary regions for organic light emitting diode (OLED) television (TV) luminance reduction

A method includes modeling, by a computing device, color saturation variations of different hues in a working color space with one or more properties of responses of a human vision system (HVS) to color stimulus. The computing device further generates one or more color saturation variation models based on the responses of the HVS to color stimulus.

Perceptual color enhancement based on properties of responses of human vision system to color stimulus

One embodiment provides a method comprising determining a first representation of a source gamut of an input content in a first (2D) device-independent color space, determining a second representation of a target gamut of a display device in a second 2D device-independent color space, and determining a color transition protection zone (TPZ) based on the source gamut and the target gamut. The method further comprises utilizing a color gamut mapping (CGM) module to perform, based on the TPZ, linear color gamut compression from the first 2D device-independent color space to the second 2D device-independent color space if the target gamut is narrower than the source gamut. The method further comprises utilizing the same CGM module to perform, based on the TPZ, linear color gamut extension from the first 2D device-independent color space to the second 2D device-independent color space if the target gamut is wider than the source gamut.

Color gamut compression and extension

One embodiment provides a computer-implemented method that includes receiving region information from a stationary region detection process for a video. A processor performs a flat region ghosting artifact removal process that updates the region information with a flat region indicator utilizing the region information and the video. The processor further performs a region based luminance reduction process utilizing the updated region information with the flat region indicator for display ghosting artifact removal and burn-in protection.

Organic light emitting diode (OLED) burn-in prevention based on stationary pixel and luminance reduction

One embodiment provides a method comprising determining multi-dimensional metadata corresponding to an input image, and determining ambient light information indicative of a level of ambient light in an ambient environment of a display device. The multi-dimensional metadata comprises a cumulative distribution function (CDF) of pixels in the input image. The method further comprises determining, based on the multi-dimensional metadata and the ambient light information, one or more gains that adaptively compensate for the level of ambient light in the ambient environment. The method further comprises generating a tone mapping function based on the one or more gains, and applying the tone mapping function to the input image to generate a tone-mapped image that adaptively compensates for the level of ambient light in the ambient environment. The tone-mapped image is provided to the display device for presentation.

HDR tone mapping based on creative intent metadata and ambient light

One embodiment provides a method comprising determining one or more coordinates representing one or more skin tones in a device-independent color space. The one or more skin tones can include one or more colors of human skin captured in one or more pieces of content. The method further comprises building a dual-core geometric model based on a distribution of the one or more skin tones in the device-independent color space. The method further comprises providing the dual-core geometric model to an electronic device for use in determining a likelihood that an input color of an input content is a skin tone. The input content is adaptively enhanced, based on the likelihood, for presentation on a display connected to the electronic device.

Skin tone protection using a dual-core geometric skin tone model built in device-independent space

One embodiment provides a method comprising determining metadata corresponding to an input image, determining a black level of a display device and a peak luminance value of the display device, and determining a tone mapping function that adaptively compensates for the black level of the display device based on the metadata, the black level of the display device, and the peak luminance value of the display device. The metadata comprises a distribution of luminance values in the input image. The black level of the display device and the peak luminance value of the display device represent a lowest luminance value and a highest luminance value, respectively, achievable on the display device. The method further comprises applying the tone mapping function to the input image to generate a tone-mapped image that adaptively compensates for the black level of the display device and provided to the display device for presentation.

Content adapted black level compensation for a HDR display based on dynamic metadata

A method, apparatus, and non-transitory computer readable medium for video tone mapping. The method includes a target display receiving a quantized video generated by a master display, the quantized video being mastered for a first range of luminance values associated with the master display; receiving metadata from a tone mapping curve parameter extraction, the metadata comprising at least one maximum value of a luminance parameter of the quantized video as mastered for the first range of luminance values; and de-quantizing the quantized video to produce a de-quantized video. The method also includes at least one processor of the target display applying a tone mapping function defined by a normalized Bezier curve to the de-quantized video; and generating, based on applying the tone mapping function, a tone mapped video mastered for a second range of luminance values associated with the target display.

One embodiment provides a method comprising determining a first representation of a source gamut of an input content in a first two-dimensional (2D) device-independent color space, determining a second representation of a target gamut of a display device in a second 2D device-independent color space, and determining a color transition protection zone (TPZ) based on the source gamut and the target gamut. The method further comprises utilizing a color gamut mapping (CGM) module to perform, based on the TPZ, linear color gamut compression from the first 2D device-independent color space to the second 2D device-independent color space if the target gamut is narrower than the source gamut. The method further comprises utilizing the same CGM module to perform, based on the TPZ, linear color gamut extension from the first 2D device-independent color space to the second 2D device-independent color space if the target gamut is wider than the source gamut.

Growing community of inventors

Tustin, CA, United States of America

Chenguang Liu