A method of region-based video-image interpolation is provided, which includes the following steps: respectively dividing each image and its subsequent image in an input video signal into first regions and second regions to obtain first regional images and second regional images; performing a motion-compensated frame-interpolation process on the first regional image and the second regional image in the same position in each image and its subsequent image to obtain an interpolated regional image; performing a frame-rate-conversion process on reference images and the interpolated regional images of each first region according to an original frame rate of each first region and a display frame rate of an output video signal to obtain a regional output image of each first region; and superimposing the regional output image generated at each output timestamp by each motion-compensated frame-interpolation circuit to generate an output image of the output video signal.

The described technology is directed towards generating a new video image sequence (e.g., for playback at 30 frames per second) based on an existing video image sequence (e.g., originated for playback at 24 frames per second). The technology is based on processing frames, e.g., adjacent pairs of frames in a four-frame sequence, to obtain candidate frames for selecting a similar candidate frame to insert into the original sequence to create the new sequence (e.g., a five-frame sequence). Aspects include selecting a repeated frame to insert or creating a new frame from existing frames to insert, to generate the new sequence based on a difference/scoring comparison.

The described technology is directed towards generating a new video image sequence (e.g., for playback at 30 frames per second) based on an existing video image sequence (e.g., originated for playback at 24 frames per second). The technology is based on processing frames, e.g., adjacent pairs of frames in a four-frame sequence, to obtain candidate frames for selecting a similar candidate frame to insert into the original sequence to create the new sequence (e.g., a five-frame sequence). Aspects include selecting a repeated frame to insert or creating a new frame from existing frames to insert, to generate the new sequence based on a difference/scoring comparison.

A method for converting a frame rate of an input video is provided. The method includes performing a motion estimation by generating at least one motion field for at least one pair of frames of the input video, wherein the at least one motion field includes a set of motion vectors for each block of a first reference frame of the input video, the set of motion vectors indicating to a second reference frame of the input video, and preparing first data for a predetermined interpolation phase for each block of an interpolated frame, where the first data include at least one parameter for a pre-trained occlusion processing (OcC) convolutional neural network (CNN), the at least one parameter being obtained based on the at least one motion field.

An image processing method includes: receiving first and second frames; generating multiple motion vectors based on the first and second frames, wherein one of the motion vectors corresponds to a first block of the first frame and a second block of the second frame; calculating a to-be-compensated position of a compensated block, a first motion vector between the compensated block and the first block, and a second motion vector between the compensated block and the second block; determining whether a sum of the to-be-compensated position, a compensation value, and the first motion vector or the second motion vector exceeds a target range in order to set a blending coefficient; modifying first data of the first block or second data of the second block based on the blending coefficient; and generating interpolated data based on the modified first data or the modified second data.

A system for using decoder information in video super resolution processing. A compressed video buffering module is used for receiving a compressed video stream and a decoder module is used for decoding the compressed video stream into an uncompressed stream and extracting motion vector information from the uncompressed stream. A video super resolution deep neural network processor module is used for processing the uncompressed stream in conjunction with the motion vector information to produce a video super resolution stream. An output buffer module is used for buffering the video super resolution stream for subsequent output.

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 method for generating a video intermediate frame, including obtaining a target video frame pair; constructing an image pyramid for each video frame in the target video frame pair; and generating an intermediate frame of the target video frame pair by using a bidirectional optical flow estimation model and a pixel synthesis model in a layer-by-layer recursive calling manner according to an order of the image pyramid from a high layer to a low layer based on the image pyramid, wherein the generating of the intermediate frame of the target video frame pair comprising: repairing a bidirectional optical flow corresponding to a previous layer using the bidirectional optical flow estimation model, and repairing a previous intermediate frame corresponding to the previous layer using the pixel synthesis model.

A projection display apparatus includes a processing circuit and an image projection display device. The processing circuit is configured to perform a dynamic motion compensation based on two successive first frame and second frame in a first video signal, in order to generate a complement frame between the first frame and the second frame. The processing circuit is further configured to combine the first frame and the complement frame into a third frame, and to decompose the third frame to generate a plurality of fourth frames and to output the fourth frames as a second video signal. A resolution of the first video signal is higher than a resolution of the second video signal. The image projection display device is configured to project and display the second video signal, in which the imaging device has an original resolution equal to the resolution of the second video signal.

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.