Dolby Laboratories Licensing Corporation

Anustup Kumar Atanu Choudhury

Robin Atkins

Tao Chen

Guan-Ming Su

Scott J Daly

Samir N Hulyalkar

Jaclyn Anne Pytlarz

Ali Zandifar

Thaddeus Beier

Robert Wanat

Ian Godin

Shruthi Suresh Rotti

A first image and a second image of different dynamic ranges are derived from the same source image. Based on a chroma sampling format of the first image, it is determined whether edge preserving filtering is to be used to generate chroma upsampled image data in a reconstructed image. If so, image metadata for performing the edge preserving filtering is generated. The first image, the second image and the image metadata are encoded into an image data container to enable a recipient device to generate the reconstructed image.

Cross-asset guided chroma reformatting for multi-asset imaging format

Methods and systems for the super resolution of high dynamic range (HDR) video are described. Given a sequence of video frames, a current frame and two or more neighboring frames are processed by a neural-network (NN) feature extraction module, followed by a NN upscaling module, and a NN reconstruction module. In parallel, the current frame is upscaled using traditional up-sampling to generate an intermediate up-sampled frame. The output of the reconstruction module is added to the intermediate up-sampled frame to generate an output frame. Additional traditional up-sampling may be performed on the output frame to match the desired up-scaling factor, beyond the up-scaling factor for which the neural network was trained.

Neural networks for high dynamic range video super-resolution

Methods and systems for generating an image quality metric are described. A reference and a test image are first converted to the ITP color space. After calculating difference images &#x394;I, &#x394;T, and &#x394;P, using the color channels of the two images, the difference images are convolved with low pass filters, one for the I channel and one for the chroma channels (I or P). The image quality metric is computed as a function of the sum of squares of filtered &#x394;I, &#x394;T, and &#x394;P values. The chroma low-pass filter is designed to maximize matching the image quality metric with subjective results.

Image quality metric for HDR images and video

A method for generating metadata for use by a video decoder for displaying video content encoded by a video encoder includes: (1) accessing a target tone mapping curve; (2) accessing a decoder tone curve corresponding to a tone curve used by the video decoder for tone mapping the video content; (3) generating a plurality of parameters of a trim-pass function used by the video decoder to apply after applying the decoder tone curve to the video content, wherein the parameters of the trim-pass function are generated to approximate the target tone curve with the combination of the trim-pass function and the decoder tone curve, and (4) generating the metadata for use by the video decoder, including said plurality of parameters of the trim-pass function.

Tone-curve optimization method and associated video encoder and video decoder

Motion characteristics related to foreground objects and background regions bordering the foreground objects in images are determined. A frame rate conversion (FRC)-related metadata portion is generated based on the motion characteristics. The FRC-related metadata portion is to be used for determining an optimal FRC operational mode with a downstream device for the images. The images are encoded into a video stream. The FRC-related metadata portion is encoded into the video stream as a part of image metadata. The video stream is caused to be transmitted to the downstream device.

Detecting motion dragging artifacts for dynamic adjustment of frame rate conversion settings

Motion characteristics related to the images are determined. A motion characteristics metadata portion is generated based on the motion characteristics, and is to be used for determining an optimal FRC operational mode with a downstream device for the images. The images are encoded into a video stream. The motion characteristics metadata portion is encoded into the video stream as a part of image metadata. The video stream is transmitted to the downstream device. The downstream receives the video stream and operates the optimal FRC operational mode to generate, based on the images, additional images. The images and the additional images are rendered on a display device at an image refresh rate different from an input image refresh rate represented by images encoded in the video stream.

Growing community of inventors

Campbell, CA, United States of America

Anustup Kumar Atanu Choudhury