The disclosure discloses a method for video frame interpolation. The method includes: obtaining a first visual semantic feature and first pixel information of a first frame, and obtaining a second visual semantic feature and second pixel information of a second frame; generating semantic optical flow information based on the first visual semantic feature and the second visual semantic feature; generating pixel optical flow information based on the first pixel information and the second pixel information; and generating an interpolation frame between the first frame and the second frame based on the semantic optical flow information and the pixel optical flow information, and interpolating the interpolation frame between the first frame and the second frame.

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 disclosure relates to the field of information display, and specifically to a method, device, computer readable storage medium, and electronic device for video frame interpolation. The method comprises: obtaining, based on two input frames, two initial optical flow maps corresponding to the two input frames; optimizing the initial optical flow maps to obtain target optical flow maps; obtaining an interpolation frame kernel, two depth maps and two context feature maps based on the two input frames; obtaining an output frame using a frame synthesis method based on the target optical flow maps, the depth maps, the context feature maps, and the interpolation frame kernel.

A device includes one or more processors configured to execute instructions to obtain motion data indicating estimated motion between a first frame and a second frame of an input sequence of image frames, and to identify, based on the motion data, any frame regions of the first frame that indicate motion greater than a motion threshold. The one or more processors are also configured to determine, based on the motion data, a motion metric associated with the identified frame regions, and to perform a determination, based on the motion metric and a size metric associated with the identified frame regions, whether to use motion-compensated frame interpolation to generate an intermediate frame. The one or more processors are further configured to generate the intermediate frame based on the determination, and to generate an output sequence of image frames that includes the intermediate frame between the first frame and the second frame.

A method comprising: receiving a high frame rate video stream of a scene; continuously dividing, in real time, the video stream into consecutive sequences of frames each; with respect to each current sequence: (i) estimating pixel motion between pairs of frames in the sequence, to calculate a current motion vector field for each pixel in the sequence, (ii) co-locating all of the pixels to current representative pixel positions associated with a desired time point in the sequence, and (iii) calculating an inter-sequence motion vector field, based on estimating motion between the current representative pixel positions and an immediately preceding sequence of the sequences; and outputting, in real time, at a rate that is lower than the high frame rate, at least one of (x) the current motion vector field, (y) the inter-sequence motion vector field, and (z) pixel values associated with the current representative pixel positions.

It is intended to make it possible to make a favorable display of, for example, images of low frame-rate content, with a high-luminance and high-contrast television set.

On the basis of an image stream having a first frame rate, for each frame, an object having luminance exceeding a luminance threshold value and/or a motion amount exceeding a motion-amount threshold value is detected as a target object. An image stream having a second frame rate larger than the first frame rate is acquired by inserting, between every pair of two consecutive frames in the image stream having the first frame rate, a predetermined number of frames of interpolated images obtained by performing motion compensation for causing the target object to sequentially move.

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.

A method includes obtaining multiple video frames. The method also includes determining whether a bi-directional optical flow between the multiple video frames satisfies an image quality criterion for bi-directional consistency. The method further includes identifying a non-linear curve based on pixel coordinate values from at least two of the video frames. The at least two video frames include first and second video frames. The method also includes generating interpolated video frames between the first and second video frames by applying non-linear interpolation based on the non-linear curve. In addition, the method includes outputting the interpolated video frames for presentation.

An apparatus includes at least one processing device configured to obtain input frames from a video. The at least one processing device is also configured to generate a forward flow from a first input frame to a second input frame and a backward flow from the second input frame to the first input frame. The at least one processing device is further configured to generate an occlusion map at an interpolated frame coordinate using the forward flow and the backward flow. The at least one processing device is also configured to generate a consistency map at the interpolated frame coordinate using the forward flow and the backward flow. In addition, the at least one processing device is configured to perform blending using the occlusion map and the consistency map to generate an interpolated frame at the interpolated frame coordinate.

A video-image-interpolation apparatus is provided, which includes at least three image-layering circuits, at least three motion-estimation circuits, a motion-estimation-filtering circuit, a motion-compensated frame-interpolation circuit, and a display-control circuit. Each motion-estimation circuit performs motion estimation on a reference image-layer sequence and a reference subtitle-layer sequence that are generated from an input video signal by each image-layering circuit. The motion-estimation-filtering circuit adaptively determines the motion-estimation circuit having the smallest motion error. The motion-compensated frame-interpolation circuit performs motion compensation to generate one or more interpolated image-layer images and one or more interpolated subtitle-layer images according to the motion vectors calculated by the motion-estimation circuit having the smallest motion error, and superimposes the one or more interpolated image-layer images and the one or more interpolated subtitle-layer images to generate interpolated images. The display-control circuit performs frame-rate conversion on the reference images and the interpolated images to obtain an output video signal.