The present disclosure relates to a video processing method, an electronic device for video playback, and a video playback system. A video processing method comprises: receiving an input video comprising a plurality of sections, and metadata associated with the input video, at least two sections of the plurality of sections of the input video having different frame rates; and performing real-time processing on the input video according to the metadata, so as to output an output video having a constant target frame rate in real time, wherein the metadata includes frames indicating various sections of the input video rate information, or the metadata includes information indicating the frame rate of each section of the input video and at least one of the following information: information indicating a target frame rate and information indicating a processing operation to be used for performing real-time processing on the input video.

The present technology relates to a display device, a signal processing device, and a signal processing method which make it possible to realize interpolation more suitable for viewing when interpolating motion between original images. Provided is a display device which includes a signal processing unit that, when an interpolation frame is generated for original frames along a time axis, the interpolation frame interpolating between the original frames, controls an interpolation rate of the interpolation frame depending on motion between the original frames in a certain direction. The present technology can be applied, for example, to a television receiver.

A method comprising: receiving a high frame rate video stream of a scene, wherein the scene comprises at least one object in motion relative to an imaging device acquiring the video stream; continuously dividing, in real time, the video stream into at least one consecutive sequences of n frames each; with respect to each current sequence: (i) estimating pixel motion between at least some pairs of frames in the sequence, (ii) calculating a motion vector field for each pixel in the sequence, (iii) generating a representative frame which co-locates all of the pixels to respective pixel positions, based on the calculated motion vector fields, and (iv) aggregating, for each of the respective pixel positions, pixel values from all frames in the sequence; and outputting, in real time, a stream of the representative frames, wherein the stream has a lower frame rate than the high frame rate.

Methods and apparatus for the generation of interpolated frames of video data. In one embodiment, the interpolated frames of video data are generated by obtaining two or more frames of video data from a video sequence; determining frame errors for the obtained two or more frames from the video sequence, determining whether the frame errors exceed a threshold value; performing a multi-pass operation; performing a single-pass operation; performing frame blending; performing edge correction; and generating the interpolated frame of image data.

A system including a motion adaptive de-interlacer, a film mode detector, and a combiner. The motion adaptive de-interlacer is configured to determine a first output by de-interlacing a plurality of interlaced frames based on at least a first motion indicator indicating motion between fields of the plurality of interlaced frames. The film mode detector is configured to determine a second output based on a film mode detected based on at least a second motion indicator indicating motion between fields of the plurality of interlaced frames. The film mode detector is further configured to output a control signal based on the second motion indicator and the film mode. The combiner is configured to combine the first output and the second output based on the control signal.

First and second spatial frame regions are identified in a sequence of motion picture image frames captured at a high frame rate. Different motion blur parameters are determined for each of the first and second spatial frame regions. First and second intermediate frame sequences having frame rates less than the capture frame rate are generated from the original frame sequence. The first motion blur parameter is applied to the first intermediate frame sequence and the second motion blur parameter is applied to the second intermediate frame sequence. The first and second spatial frame regions in the corresponding first and second intermediate frame sequences are composited to produce an output frame sequence having different motion blur in different regions of the scene.

A method of detecting a frame rate of a source, including: receiving frames of a source provided at an input frame rate; providing the frames to a window having a predetermined length to detect the number of original frames included within the window having the length; and multiplying the input frame rate divided by the length and the number of original frames.

An image processing device includes a flicker estimating circuit, a control circuit and an image processing circuit. The flicker estimating circuit estimates a flicker level of a frame according to at least one set of information corresponding to the frame to generate an estimated flicker result. The control circuit is coupled to the flicker estimating circuit, and generates at least one control signal according to the flicker level. The image processing circuit is coupled to the control circuit, and performs image processing on the frame according to the control signal.

A method of detecting a frame rate of a source, including: receiving frames of a source provided at an input frame rate; providing the frames to a window having a predetermined length to detect the number of original frames included within the window having the length; and multiplying the input frame rate divided by the length and the number of original frames.

Video interpolation is used to predict one or more intermediate frames at timesteps defined between two consecutive frames. A first neural network model approximates optical flow data defining motion between the two consecutive frames. A second neural network model refines the optical flow data and predicts visibility maps for each timestep. The two consecutive frames are warped according to the refined optical flow data for each timestep to produce pairs of warped frames for each timestep. The second neural network model then fuses the pair of warped frames based on the visibility maps to produce the intermediate frame for each timestep. Artifacts caused by motion boundaries and occlusions are reduced in the predicted intermediate frames.