The disclosed system modifies luminance of a display associated with a selective screen. The display provides a camera with an image having resolution higher than the resolution of the display by presenting multiple images while the selective screen enables light from different portions of the multiple images to reach the camera. The resulting luminance of the recorded image is lower than a combination of luminance values of the multiple images. The processor obtains a criterion indicating a property of the input image where image detail is unnecessary. The processor detects a region of the input image satisfying the criterion, and determines a region of the selective screen corresponding to the region of the input image. The processor increases the luminance of the display by disabling the region of the selective screen corresponding to the region of the input image.

An encoding device evaluates a plurality of processing and/or post-processing algorithms and/or methods to be applied to a video stream, and signals a selected method, algorithm, class or category of methods/algorithms either in an encoded bitstream or as side information related to the encoded bitstream. A decoding device or post-processor utilizes the signaled algorithm or selects an algorithm/method based on the signaled method or algorithm. The selection is based, for example, on availability of the algorithm/method at the decoder/post-processor and/or cost of implementation. The video stream may comprise, for example, downsampled multiplexed stereoscopic images and the selected algorithm may include any of upconversion and/or error correction techniques that contribute to a restoration of the downsampled images.

Embodiments disclosed herein relate to device and method for processing frames. For example, a buffer of a device is arranged to store a plurality of rendered frames rendered at a frame rendering rate and a time stamp for each of rendered frames. A compositor of a device is arranged to obtain a timestamp of a synchronisation signal for synchronising the display of frames with a display refresh rate. In response to obtaining a timestamp of a synchronisation signal, a compositor is arranged to trigger access to a buffer to obtain two rendered frames having timestamps closest to a timestamp of a synchronisation signal. An interpolator of a device is arranged to generate an interpolated rendered frame for display by performing an interpolation operation using two rendered frames. An interpolation operation takes into account the difference between timestamps of each of two rendered frames and a timestamp of a synchronisation signal.

Systems, methods, and computer-readable media for context-aware synthesis for video frame interpolation are provided. A convolutional neural network (ConvNet) may, given two input video or image frames, interpolate a frame temporarily in the middle of the two input frames by combining motion estimation and pixel synthesis into a single step and formulating pixel interpolation as a local convolution over patches in the input images. The ConvNet may estimate a convolution kernel based on a first receptive field patch of a first input image frame and a second receptive field patch of a second input image frame. The ConvNet may then convolve the convolutional kernel over a first pixel patch of the first input image frame and a second pixel patch of the second input image frame to obtain color data of an output pixel of the interpolation frame. Other embodiments may be described and/or claimed.

A video frame interpolation method and device, and a computer-readable storage medium are described. The method includes: inputting at least two image frames into a video frame interpolation model to obtain at least one frame-interpolation image frame, training the initial model using a first loss to obtain a reference model, copying the reference model to obtain three reference models with shared parameters, selecting different target sample images according to a preset rules to train the first/second reference model to obtain a first/second frame-interpolation result; selecting third target sample images from the first/second frame-interpolation result to train the third reference model to obtain the frame-interpolation result, obtaining a total loss of the first training model based on the frame-interpolation result and the sample images, adjusting parameters of the first training model based on the total loss, and using a parameter model via a predetermined number of iterations as the video frame interpolation model.

For sharpening an input image by up-converting the input image in order to increase the number of pixels of an image and generating a frequency component higher than a frequency component contained in an input image signal representing the input image, the number of multipliers is reduced, thereby achieving significant downsizing of an apparatus and cost reduction. An image processing apparatus includes a path on a base image side for up-converting the input image signal and a path on a sharpening processing side for carrying out nonlinear arithmetic processing on the input image signal. The path on the sharpening processing side includes an up-converter at a subsequent stage of at least one filter, after which the nonlinear arithmetic processing is carried out. The at least one filter may be either a two-dimensional low pass filter for noise removal or a high pass filter for removing a DC component.

An encoding device evaluates a plurality of processing and/or post-processing algorithms and/or methods to be applied to a video stream, and signals a selected method, algorithm, class or category of methods/algorithms either in an encoded bitstream or as side information related to the encoded bitstream. A decoding device or post-processor utilizes the signaled algorithm or selects an algorithm/method based on the signaled method or algorithm. The selection is based, for example, on availability of the algorithm/method at the decoder/post-processor and/or cost of implementation. The video stream may comprise, for example, downsampled multiplexed stereoscopic images and the selected algorithm may include any of upconversion and/or error correction techniques that contribute to a restoration of the downsampled images.

The disclosed system and method can increase resolution of a display in postprocessing. The processor can obtain multiple images presented on a display, where the display is configured to present the multiple images at a first frame rate higher than a frame rate needed to form a perception of motion. The processor can obtain a mask corresponding to one or more images among the multiple images, where the mask indicates a portion of the one or more images among the multiple images to include in an output image. The processor can increase resolution of the display in proportion to the number of multiple images presented to the display by combining, based on the mask, the one or more images among the multiple images to obtain the output image.

A method for processing video frames, a video processing chip, and a Motion Estimation/Motion Compensation (MEMC) chip are provided. The method performed by the video processing chip includes obtaining multiple video frames and adjusting each video frame from a first resolution to a second resolution. The method also includes inserting at least one invalid frame into the multiple video frames according to a second frame rate, so that a frame rate of a transport frame stream is the second frame rate; and sending the transport frame stream to an MEMC chip. The video processing chip and the MEMC chip may perform transmission of a frame stream according to an interface frequency corresponding to a resolution and a frame rate that are agreed upon.

An image processing apparatus includes a storage unit that stores a look-up table having association information for associating at least one first image with at least one second image that is an image whose load on a brain has been adjusted, an image accepting unit that accepts at least one image, a mapping unit that acquires a whole or part of one or more second images associated with a whole or part of the at least one image accepted by the image accepting unit, using association information from among the one or more pieces of association information, and an image output unit that outputs at least one output image, which is the whole of the at least one second image acquired by the mapping unit or a group of part of the at least one second image acquired by the mapping unit.