Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Thank you! Very nice interpolation #4

Open
jhogsett opened this issue Mar 12, 2023 · 18 comments
Open

Thank you! Very nice interpolation #4

jhogsett opened this issue Mar 12, 2023 · 18 comments

Comments

@jhogsett
Copy link

jhogsett commented Mar 12, 2023

Hi, Thank You for your great video frame interpolation model!

I wanted to try it out, and compare it to VFIformer. I had previously created a web-based tool: "VFIformer-WebUI". It made sense to me to make a version of my tool that uses your model instead.

I've created "EMA-VFI-WebUI", a version of my application that uses your 2x interpolation model:

https://github.com/jhogsett/EMA-VFI-WebUI

It makes no changes to your code, and just needs to be overlaid on top. The readme file has details on how to install and run it. I think this will make it easy and fun to use your model and also compare it with VFIformer. My original application is at https://github.com/jhogsett/VFIformer-WebUI.

@GuozhenZhang1999
Copy link
Collaborator

Wow! This tool looks fantastic! Thank you so much for recognizing our work, and we'll definitely add a link to your tool in the README file. Personally, I was thinking that it might be even simpler and more efficient if we could compare the effectiveness of different models at the same time. Thanks again for sharing your awesome creation with us!

@jhogsett
Copy link
Author

You're welcome! Thank you for your amazing research and model, and thanks for the link!

I have a keen interest in digitized film restoration. I'm very happy to find a model like yours.

I have started working on some comparisons myself, recreating some of my previous work with VFIformer. I'm happy to share some results here when I have them.

@Daniel-Kelvich
Copy link

@jhogsett I would be interested to see your comparison!

@GuozhenZhang1999
Copy link
Collaborator

You're welcome! Thank you for your amazing research and model, and thanks for the link!

I have a keen interest in digitized film restoration. I'm very happy to find a model like yours.

I have started working on some comparisons myself, recreating some of my previous work with VFIformer. I'm happy to share some results here when I have them.

Looking forward to seeing your progress! We will also provide a video that compares our method with a few others, and we hope it will be helpful to you!

@jhogsett
Copy link
Author

jhogsett commented Mar 12, 2023

@GuozhenZhang1999 @Daniel-Kelvich

Here's my initial test, which used to evaluate EMA-VFI. Background:

  • My tool has a GIF-to-MP4 feature
  • It increases the frame rate using frame interpolation, and increases the frame size using Real-ESRGAN
  • Note: it uses simple binary interpolation (I plan to use your multi-interference model in a future version)

Original GIF:
https://user-images.githubusercontent.com/825994/220933026-3fe6bf25-8be7-490e-a90b-85a151e6b156.gif

VFIformer MP4:
https://user-images.githubusercontent.com/825994/224549158-7df76e49-28ec-4a3c-9b2b-4699729bd84f.mp4

EMA-VFI MP4:
https://user-images.githubusercontent.com/825994/224548062-4cad649c-5cdb-4f66-936d-e2296eb0fbc8.mp4

(Both examples have been created just now using the latest code. Rate increased 8X, size increased 4X)

What I observe:

  • EMA-VFI is noticeably smoother, especially around 0:05

@GuozhenZhang1999
Copy link
Collaborator

Thank you for providing such a comprehensive example! Based on the results, it appears that our model indeed has better temporal consistency. If you are willing, please feel free to continue updating your progress on this post. Although we may not reply to each one individually, please know that we greatly appreciate your valuable contribution!

@jhogsett
Copy link
Author

You're welcome @GuozhenZhang1999 ! I will post some more examples here for you and others to enjoy. I notice also that the EMA-VFI version looks slightly less dull than the VFIformer version.

@jhogsett
Copy link
Author

Here's another similar example.

VFIformer: https://youtube.com/shorts/IZdEITUQx3U?feature=share

EMA-VFI: https://youtube.com/shorts/PLkOUxiFAuk?feature=share

I prefer the EMA-VFI version:

  • The motion seems smoother and more fluid
  • The image looks less dull than the VFIformer version
  • The sudden disappearance of objects seems to be handled better (noticeable near the end)

Original GIF:
musicmovesyou-escape-to-music

@jhogsett
Copy link
Author

I've just posted a new YouTube video with a live comparison of EMA-VFI, VFIformer (footage inflated to 480 FPS) and the original footage (@ 30 FPS) https://youtube.com/shorts/n-YCv37bU9s?feature=share

@jhogsett
Copy link
Author

Here is another video, same format. This time it's a police chase (footage inflated from 24 FPS to 768 FPS). https://youtube.com/shorts/En5VsJNVmnE?feature=share

@jhogsett
Copy link
Author

Here is one more: https://youtube.com/shorts/P5TuFfLWIIM?feature=share

This is a carnival at night inflated from 15 FPS to 480 FPS (like inflating a 30 FPS video to 1000 FPS!).

EMA-VFI shows its quality very well, especially near the end, when the fast flashing lights seem to confuse VFIformer.

@jhogsett
Copy link
Author

Three videos demonstrating the recovery of original video footage from time lapse videos using VFIformer and EMA-VFI:

Traffic: https://youtube.com/shorts/rwiyvQplQ28?feature=share

Carpenter: https://youtube.com/shorts/Emk3x-8jQNc?feature=share

Airplanes Landing: https://youtube.com/shorts/DRvn-a0u4zE?feature=share

@jhogsett
Copy link
Author

The last of my video comparison series between VFIformer and EMA-VFI. For the final videos I chose very challenging content: ocean water, first-person POV, fast movement.

Electric Surfboard: https://www.youtube.com/shorts/BzBHsiEnNxg

Kite Surfer: https://www.youtube.com/shorts/W5otlVo989I

Rollercoaster: https://www.youtube.com/shorts/nb6uTRohPgU

@semel1
Copy link

semel1 commented Jul 28, 2023

If you can provide me with your original videos (preferably non-vertical) - I could make comparison using RIFE.

@jhogsett
Copy link
Author

jhogsett commented Jul 28, 2023

@semel1 each of the above YouTube videos includes a link to the royalty-free video used to create the comparison from MotionArray.com. Free watermarked preview versions can be downloaded without needing an account.

In particular I would be interested in seeing a version of this study, where the video has been inflated 32X to 768 FPS: https://www.youtube.com/shorts/En5VsJNVmnE

Edit: here's the link to the video: "The Pursuit Slaloms Left And Right" https://motionarray.com/stock-video/the-pursuit-slaloms-left-and-right-1171307/

@semel1
Copy link

semel1 commented Jul 29, 2023

@semel1 each of the above YouTube videos includes a link to the royalty-free video used to create the comparison from MotionArray.com. Free watermarked preview versions can be downloaded without needing an account.

In particular I would be interested in seeing a version of this study, where the video has been inflated 32X to 768 FPS: https://www.youtube.com/shorts/En5VsJNVmnE

Edit: here's the link to the video: "The Pursuit Slaloms Left And Right" https://motionarray.com/stock-video/the-pursuit-slaloms-left-and-right-1171307/

Please take a look at https://youtu.be/mFU8z-DSTds

@jhogsett
Copy link
Author

Thank you. I'm seeing a significant loss of detail in your example, especially noticeable in the final part with the close-up of the car grill.

@2blackbar
Copy link

Hey man can you do one click nstaler with own venv so we dont have to deal with incompatible dependencies versions clashin?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants