Skip to content

Rya-man/Video-stabalization

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Advanced Video Stabilization without content loss

Problem

Major consumer-wide video stabilization programs zoom/crop to readjust for the camera movement to get to a stable footage. But that results in loss of content and data.

Our Solution

We work on each frame individually. We extract all the frames, and recompensate for the lost data while stabilization using outpainting, diffusion models and extrapolation.

Feature given by mentor to implement

After stablizing a video with moviepy, vidgear there are black edges that represent lost data. Our task was to fill that sections on each frame. We solved it by using diffusion.

                                      INPUT VIDEO:

INPUT VIDEO:

                        STABILISED VIDEO WITH PRIMITIVE STABILISATION:

STABILISED VIDEO WITH PRIMITIVE STABILISATION:

                            STABILISED VIDEO WITH FILLED EDGES:

STABILISED VIDEO WITH FILLED EDGED:

Additional Feature

FPS interpolation to increase frame rate to a defined rate.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published