Enhancing the resolution and quality of sequential digital images
First Claim
1. A method, comprising:
- receiving as input a sequence of two or more low resolution video frames;
creating pixel motion trajectories for the sequence of video frames by registering the frames, the created pixel motion trajectories being relative to a current frame of the received sequence, and including;
calculating a global transformation, relative to the current frame, for the received sequence of video frames, such that the creating of the pixel motion trajectories is based on the calculated global transformation;
performing spatial interpolation on the registered frames from points that are not on a regular grid to points that are on a regular grid, wherein the results of the spatial interpolation comprise noisy observations on the regular grid;
performing temporal approximation on the noisy observations, wherein the results of the temporal approximation are high resolution video frames; and
outputting a sequence of high resolution video frames.
3 Assignments
0 Petitions
Accused Products
Abstract
In particular embodiments, a process relating to the creation of a high-resolution video from a low-resolution video. In a particular embodiment, the process receives as input a sequence of low-resolution video frames. The process first determines a matching score for consecutive frames in the sequence, where the matching score is based on a preliminary global transformation between consecutive frames. From the matching scores, the process determines a set of matching windows and relative-motion estimates and then uses the set and estimates to calculate more thorough global transformations and any residual relative-motion which can be explained using independent object motion and/or optical flow. The process uses the latter global transformation and any independent object motion and/or optical flow to create motion trajectories and to generate high-resolution frames by interpolating low-resolution frames at trajectory-defined points, using regular-to-irregular spatio-temporal interpolation. The process then restores the frames, using deblurring, and outputs them.
-
Citations
19 Claims
-
1. A method, comprising:
-
receiving as input a sequence of two or more low resolution video frames; creating pixel motion trajectories for the sequence of video frames by registering the frames, the created pixel motion trajectories being relative to a current frame of the received sequence, and including; calculating a global transformation, relative to the current frame, for the received sequence of video frames, such that the creating of the pixel motion trajectories is based on the calculated global transformation; performing spatial interpolation on the registered frames from points that are not on a regular grid to points that are on a regular grid, wherein the results of the spatial interpolation comprise noisy observations on the regular grid; performing temporal approximation on the noisy observations, wherein the results of the temporal approximation are high resolution video frames; and outputting a sequence of high resolution video frames. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. One or more non-transitory computer-readable media comprising computer-readable instructions for execution that when executed by one or more processors cause carrying out a method comprising:
-
receiving as input a sequence of two or more low resolution video frames; creating pixel motion trajectories for the sequence of video frames by registering the frames, the creating pixel motion trajectories being relative to a current frame of the received sequence of video frames, and including; calculating a global transformation, relative to the current frame, for the received sequence of video frames, such that the creating of the pixel motion trajectories is based on the calculated global transformation; performing spatial interpolation on the registered frames from points that are not on a regular grid to points that are on a regular grid, wherein the results of the spatial interpolation comprise noisy observations on the regular grid; performing temporal approximation on the noisy observations, wherein the results of the temporal approximation are high resolution video frames; and outputting a sequence of high resolution video frames. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19)
-
Specification