A video signal processing method includes obtaining a first linear luminance signal based on a first linear red green blue (RGB) signal corresponding to a video signal, converting the first linear luminance signal into a first non-linear luminance signal, performing a piecewise luminance mapping on the first non-linear luminance signal to obtain a second non-linear luminance signal, converting the second non-linear luminance signal into a second linear luminance signal, calculating a luminance gain between the second linear luminance signal and the first linear luminance signal, and obtaining, based on a product of the luminance gain and the first linear RGB signal, an RGB display signal corresponding to the video signal.

Disclosed is an electronic device including a display module and a processor. The processor is configured to obtain a first video frame and a bypass control value for the first video frame and determine whether to perform frame rate conversion (FRC) processing using the first video frame based on the bypass control value. Based on a determination that the bypass control value is set to a first value indicating bypass of the FRC processing, the processor is configured to display the first video frame. Based on a determination that the bypass control value is set to a second value indicating the FRC processing, the processor is configured to generate an interpolation frame using the first video frame and a second video frame after the first video frame, and display the first video frame, the interpolation frame, and the second video frame.

Disclosed is an electronic apparatus. The electronic apparatus includes a memory configured to store a plurality of frames included in an input image and a processor configured to: identify whether one frame of the plurality of frames is a first interpolated frame generated based on at least two frames from remaining frames of the plurality of frames, and select a reference frame to be used in frame interpolation of the plurality of frames based on the first interpolated frame being identified.

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.

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.

Disclosed is an electronic apparatus. The electronic apparatus includes a memory configured to store a plurality of frames included in an input image and a processor configured to: identify whether one frame of the plurality of frames is a first interpolated frame generated based on at least two frames from remaining frames of the plurality of frames, and select a reference frame to be used in frame interpolation of the plurality of frames based on the first interpolated frame being identified.

Methods and systems provide for representation of natural eye contact within a video conferencing session. In one embodiment, a method provides, for a physical space, a connection to a remote video conferencing session with one or more remote participants, the physical space including transparent video screens, cameras positioned behind the transparent screens, and participants. The method provides a connection to a remote video conferencing session with one or more remote participants, then displays, at each of the transparent screens, streamed videos of the one or more remote participants in every other frame of the video such that each screen alternates between displaying a frame of the remote participant and a transparent frame. The method then captures, via the cameras, video frames of the one or more participants in the physical space during the display of the transparent frames, and transmits the captured video frames of the participants to be displayed at one or more remote screens viewed by the one or more remote participants.

A method includes receiving an input video stream and providing, to a convolutional neural network (CNN), multiple image frames of the video stream including a target pair of consecutive frames, a frame immediately preceding the target pair, and a frame immediately following the target pair. The method includes generating, by the CNN, multiple interpolated image frames by performing 3D space-time convolution on the multiple image frames and outputting a video stream in which the interpolated image frames are inserted between the frames of the target pair. The convolution may include passing a 3D filter over the multiple image frames in common width and height dimensions, and in a depth dimension representing the number of frames. Generating the interpolated image frames may include generating image data for multiple color channels in respective convolutional layers. The CNN may be trained to predict non-linear movements that occur over multiple image frames.

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.

There is disclosed in one example a video processor, including: an input buffer to receive an input image; a slicer circuit to divide the input image into a plurality of N vertical slices; N parallel input buffers for de-rasterization; N parallel image scalers, wherein each scaler is hardware configured to scale in a raster form, one of the N vertical slices according to an image scaling algorithm; N parallel output buffers for rerasteriztion; and an output multiplexer to combine the scaled vertical slices into a combined scaled output image.