copilot/OpenSeeFace
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fixed typo.

Browse source
This commit is contained in:
Emiliana 2022-09-05 14:15:52 +02:00 • committed by GitHub
parent 5936b487a7
commit 1f8b83feef
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -18,7 +18,7 @@ Since the landmarks used by OpenSeeFace are a bit different from those used by o
Anecdotically, OpenSeeFace performs well in adverse conditions (low light, high noise, low resolution) and keeps tracking faces through a very wide range of head poses. Compared to MediaPipe, OpenSeeFace landmarks remain more stable in challenging conditions and it accurately represents a wider range of mouth poses. However, tracking of the eye region can be a bit worse.
I ran OpenSeeFace on a sample clip from the video presentation for [3D Face Reconstruction with Dense Landmarks](https://microsoft.github.io/DenseLandmarks/) by Wood et al. to compare it to MediaPipe and their approach. You can watch the result [ħere](https://cdn.discordapp.com/attachments/720652345540870237/1016320201807106118/OSFMediaPipe3DFR.mp4).
I ran OpenSeeFace on a sample clip from the video presentation for [3D Face Reconstruction with Dense Landmarks](https://microsoft.github.io/DenseLandmarks/) by Wood et al. to compare it to MediaPipe and their approach. You can watch the result [here](https://cdn.discordapp.com/attachments/720652345540870237/1016320201807106118/OSFMediaPipe3DFR.mp4).
# Usage