[Feature] Add video interpolation demo

[Yshuo-Li]

No description provided.

[codecov]

Codecov Report

Merging #688 (3e96d3d) into cain-config (ae37f0a) will increase coverage by 0.12%.
The diff coverage is 92.53%.

@@               Coverage Diff               @@
##           cain-config     #688      +/-   ##
===============================================
+ Coverage        81.76%   81.88%   +0.12%     
===============================================
  Files              211      212       +1     
  Lines            11888    11947      +59     
  Branches          1910     1920      +10     
===============================================
+ Hits              9720     9783      +63     
+ Misses            1872     1865       -7     
- Partials           296      299       +3     

Flag	Coverage Δ
unittests	81.86% <92.53%> (+0.12%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
mmedit/apis/video_interpolation_inference.py	91.22% <91.22%> (ø)
mmedit/apis/__init__.py	100.00% <100.00%> (ø)
...t/models/video_interpolators/basic_interpolator.py	97.32% <100.00%> (+0.02%)	⬆️
mmedit/models/video_interpolators/cain.py	100.00% <0.00%> (+4.00%)	⬆️
mmedit/apis/matting_inference.py	39.02% <0.00%> (+19.51%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update ae37f0a...3e96d3d. Read the comment docs.

[Yshuo-Li]

How about generating the sequence in each method?

[ckkelvinchan]

How about generating the sequence in each method?

I think the best would be to incorporate it into the data pipeline. But I am not sure whether it is easy to accomplish.