Systems and methods for generating interpolated images are disclosed. In examples, image features are extracted from a first image and a second image; such image features may be warped using first and second plurality of parameters. A first candidate intermediate frame may be generated based on the warped first features and the warped second features. Multi-scale features associated with the image features extracted from the first image and the second image may be obtained and warped using the first and second plurality of parameters. A second candidate intermediate frame may be generated based on the warped first multi-scale features and the warped second multi-scale features. By blending the first candidate intermedia frame with the second candidate intermediate frame, an interpolated image may be generated.

A frame processor may generate a mask based on one or more static regions of a first set of frames of a plurality of previous frame and adjust the mask to at least one of determine alpha data or conceal distorted content associated with the one or more static regions of the first set of frames. The distorted content may be caused by extrapolation of a frame from a second set of frames of the plurality of previous frames. The frame processor may generate a composite frame based on application of at least one of the mask or the alpha data to a previous frame of the plurality of frames, and application of the previous frame based on the at least one of the mask or the alpha data to the frame extrapolated from the second set of frames of the plurality of previous frames.

A frame processor may generate a mask based on one or more static regions of a first set of frames of a plurality of previous frame and adjust the mask to at least one of determine alpha data or conceal distorted content associated with the one or more static regions of the first set of frames. The distorted content may be caused by extrapolation of a frame from a second set of frames of the plurality of previous frames. The frame processor may generate a composite frame based on application of at least one of the mask or the alpha data to a previous frame of the plurality of frames, and application of the previous frame based on the at least one of the mask or the alpha data to the frame extrapolated from the second set of frames of the plurality of previous frames.

A frame processor may generate a mask based on one or more static regions of a first set of frames of a plurality of previous frame and adjust the mask to at least one of determine alpha data or conceal distorted content associated with the one or more static regions of the first set of frames. The distorted content may be caused by extrapolation of a frame from a second set of frames of the plurality of previous frames. The frame processor may generate a composite frame based on application of at least one of the mask or the alpha data to a previous frame of the plurality of frames, and application of the previous frame based on the at least one of the mask or the alpha data to the frame extrapolated from the second set of frames of the plurality of previous frames.

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.

A method for selecting a reference frame, an electronic device, and a storage medium. The method includes: calculating a sum of absolute values of pixel brightness differences of corresponding pixel locations in a current frame and a previous frame in a video; determining frame attribute of the current frame based on the sum of absolute values of pixel brightness differences, the frame attribute including a raw frame and a duplicate frame; counting a number of raw frames in M historical frames previous to the current frame; obtaining a current frame interpolation step size based on the number of raw frames in the M historical frames; obtaining a next frame phase to be interpolated based on a current frame interpolation phase and the current frame interpolation step size; and determining an interpolation reference frame based on the next frame to be interpolated.

The present application provides a method of processing video data. The method of processing video data includes obtaining a frame of video including M numbers of first pixel groups along a first direction, each of the M numbers of first pixel groups including N numbers of pixels along a second direction, M and N being positive integers; determining Q numbers of first pixel sets for each respective one of the M numbers of first pixel groups; assigning Q numbers of pixels values respectively to the Q numbers of first pixel sets for each respective one of the M numbers of first pixel groups; generating M numbers of second pixel groups respectively for the M numbers of first pixel groups; and obtaining a processed frame of video including the M numbers of second pixel groups along the first direction.

A method for selecting a reference frame, an electronic device, and a storage medium. The method includes: calculating a sum of absolute values of pixel brightness differences of corresponding pixel locations in a current frame and a previous frame in a video; determining frame attribute of the current frame based on the sum of absolute values of pixel brightness differences, the frame attribute including a raw frame and a duplicate frame; counting a number of raw frames in M historical frames previous to the current frame; obtaining a current frame interpolation step size based on the number of raw frames in the M historical frames; obtaining a next frame phase to be interpolated based on a current frame interpolation phase and the current frame interpolation step size; and determining an interpolation reference frame based on the next frame to be interpolated.

The present application provides a method of processing video data. The method of processing video data includes obtaining a frame of video including M numbers of first pixel groups along a first direction, each of the M numbers of first pixel groups including N numbers of pixels along a second direction, M and N being positive integers; determining Q numbers of first pixel sets for each respective one of the M numbers of first pixel groups; assigning Q numbers of pixels values respectively to the Q numbers of first pixel sets for each respective one of the M numbers of first pixel groups; generating M numbers of second pixel groups respectively for the M numbers of first pixel groups; and obtaining a processed frame of video including the M numbers of second pixel groups along the first direction.

An electronic apparatus includes a memory configured to store an input image and at least one processor configured to obtain two consecutive frames of the input image as input frames; obtain a first interpolation frame of the input frames and a first confidence corresponding to the first interpolation frame based on a first interpolation method; obtain a second interpolation frame of the input frames and a second confidence corresponding to the second interpolation frame based on a second interpolation method that is different from the first interpolation method; obtain weights corresponding to the first interpolation frame and the second interpolation frame, based on the first confidence and the second confidence, respectively; and obtain an output image based on the weights.