Emiliana
|
baf4d546c0
|
Added hybrid lip sync/mouth tracking to OpenSeeVRMDriver.
|
2020-06-27 13:13:45 +02:00 |
|
Emiliana
|
8d2df41d24
|
More settings for eyebrow tracking.
|
2020-06-26 18:11:41 +02:00 |
|
Emiliana
|
d8d0b0bff0
|
When --max-feature-updates is enabled, feature stats are no longer discarded upon detecting a new face.
|
2020-06-25 17:19:51 +02:00 |
|
Emiliana
|
d6cfa7bed3
|
Merge branch 'master' of github.com:emilianavt/OpenSeeFace
|
2020-06-24 12:29:58 +02:00 |
|
Emiliana
|
0690bdd15e
|
Face 3D point adaption can be disabled and feature adaptability can be limited now.
|
2020-06-24 12:29:33 +02:00 |
|
Emiliana
|
221cb307f4
|
Added a note about current OpenSeeFaceDemo status
|
2020-06-23 01:46:08 +02:00 |
|
Emiliana
|
161363682d
|
OpenSeeVRMDriver now supports linked eye blinking.
|
2020-06-21 19:02:32 +02:00 |
|
Emiliana
|
bed95be58c
|
OpenSeeVRMDriver now properly resets blendshape clips each frame and correctly mixes in eyebrows for models with custom VRM blendshape clips.
|
2020-06-21 13:13:06 +02:00 |
|
Emiliana
|
5480966ef0
|
OpenSeeIKTarget is now more robust against tracking errors that occur while the camera is still starting up.
|
2020-06-21 13:11:53 +02:00 |
|
Emiliana
|
80081bed1f
|
OpenSeeVRMDriver now properly combines VRM blendshape clips for expressions and mouth animation.
|
2020-06-18 12:13:50 +02:00 |
|
Emiliana
|
09f75c450b
|
This fixes a memory leak in OpenSeeShowPoints.
|
2020-06-17 22:18:53 +02:00 |
|
Emiliana
|
7b4d3e1b11
|
This fixes various smoothness issues with the eyebrow tracking.
|
2020-06-10 20:07:40 +02:00 |
|
Emiliana
|
4d58c3304d
|
VRM blendshape clips with the names "Brows up" and "Brows down" are now prioritized over auto detected blendshapes. This also fixes a bug with the interpolation code.
|
2020-06-08 11:58:27 +02:00 |
|
Emiliana
|
fe6690543e
|
Eyebrow tracking can now be controlled on a per expression basis.
|
2020-06-07 18:49:10 +02:00 |
|
Emiliana
|
87b4079d68
|
This makes the eyebrowStrength parameter actually do something.
|
2020-06-07 17:33:56 +02:00 |
|
Emiliana
|
09020bbdbe
|
Merge branch 'master' of github.com:emilianavt/OpenSeeFace
|
2020-06-07 17:18:06 +02:00 |
|
Emiliana
|
47b5bbefae
|
More people helped with testing
|
2020-06-07 17:17:55 +02:00 |
|
Emiliana
|
f5af947d5b
|
There is now better smoothing for visemes and basic eyebrow tracking for VRoid and Cecil Henshin models.
|
2020-06-07 17:16:15 +02:00 |
|
Emiliana
|
f5c59231c5
|
A new sample video was added to the README
|
2020-05-26 16:08:47 +02:00 |
|
Emiliana
|
b09639b71d
|
Lip sync should now be able to handle stereo audio where one track is silent, but Unity's microphone input is forced to mono audio anyways. It still improves things with canned audio.
|
2020-05-22 18:51:34 +02:00 |
|
Emiliana
|
e9f0c35f0b
|
Sample images were added to the README
|
2020-05-21 18:25:43 +02:00 |
|
Emiliana
|
a3a45a8e89
|
The captions were missing on results pictures
|
2020-05-21 18:19:12 +02:00 |
|
Emiliana
|
013deaa24e
|
Sample images with face detection and landmark results
|
2020-05-21 18:13:44 +02:00 |
|
Emiliana
|
76b621a82a
|
Merge branch 'master' of github.com:emilianavt/OpenSeeFace
|
2020-05-20 17:28:17 +02:00 |
|
Emiliana
|
d3d461bc3e
|
The OpenSeeIKTarget can now skip tracking frames with sudden rotation changes.
|
2020-05-20 17:28:00 +02:00 |
|
Emiliana
|
95763bfeaa
|
Update README.md
|
2020-05-20 02:08:29 +02:00 |
|
Emiliana
|
0756568df1
|
The expression toggle hotkeys in OpenSeeVRMDriver were supposed to require both the shift and ctrl keys to be pressed, but would work with either. This fixes that.
|
2020-05-19 14:06:54 +02:00 |
|
Emiliana
|
e33e8587e0
|
This fixes the calculations for the smooth transitions between expressions.
|
2020-05-17 16:39:59 +02:00 |
|
Emiliana
|
f7551298af
|
Merge branch 'master' of github.com:emilianavt/OpenSeeFace
|
2020-05-17 15:58:32 +02:00 |
|
Emiliana
|
d3a903da8e
|
The OpenSeeVRMDriver example now supports smooth transitions between expressions.
|
2020-05-17 15:58:04 +02:00 |
|
Emiliana
|
f47e78d53e
|
Some outdated information was left in the README.
|
2020-05-01 11:56:31 +02:00 |
|
Emiliana
|
c9c5193a55
|
The dataset used to train the face detection model was missing from the README.
|
2020-05-01 11:48:22 +02:00 |
|
Emiliana
|
8145e4b0ac
|
The model definitions are now updated to match the currently used models as mentioned in issue #1
|
2020-04-30 15:39:58 +02:00 |
|
Emiliana
|
b43f281ef9
|
The OpenSeeShowPoints component can now draw lines between points to better visualize the shape of the face.
|
2020-04-05 15:03:52 +02:00 |
|
Emiliana
|
cf49ba5468
|
Unity components that rely on 3D points now ignore tracking data for frames with high 3D fitting error.
|
2020-03-30 16:44:33 +02:00 |
|
Emiliana
|
ea735ffdde
|
This adds a new medium quality model. Unused models were removed and the README.md file updated.
|
2020-03-29 15:56:54 +02:00 |
|
Emiliana
|
b6fc931723
|
To make the IK target's calibration easily callable from a button, it now has a Calibrate method.
Thanks to Deat for noting that this would be useful!
|
2020-03-28 18:13:35 +01:00 |
|
Emiliana
|
8c547a3b39
|
Some slight optimizations for multi face tracking.
|
2020-03-28 14:57:56 +01:00 |
|
Emiliana
|
b6554ddeaa
|
This adds a new fastest model.
|
2020-03-28 13:14:50 +01:00 |
|
Emiliana
|
4268abb00a
|
The basic 3D point model used for 3D point fitting is now based on data from fitting the points to head-pose-face-detection-female.mp4 over multiple iterations
|
2020-03-26 19:00:33 +01:00 |
|
Emiliana
|
60fb3aac31
|
Lower overlap threshold.
|
2020-03-25 23:02:23 +01:00 |
|
Emiliana
|
3f85a44f13
|
Slightly higher threshold.
|
2020-03-25 22:57:13 +01:00 |
|
Emiliana
|
9bd3fcc617
|
When multiple faces were close to each other, some of them were removed by accident. This fixes that.
|
2020-03-25 22:52:28 +01:00 |
|
Emiliana
|
5c118347b6
|
New and improved tracking model and confidence value visualization.
|
2020-03-25 17:03:30 +01:00 |
|
Emiliana
|
b0a61b41d5
|
RetinaFace inference is now done at full resolution without padding.
|
2020-03-22 18:01:21 +01:00 |
|
Emiliana
|
381d3b67ec
|
Small bugfix.
|
2020-03-22 14:20:17 +01:00 |
|
Emiliana
|
14b4bd9122
|
As the Haar Cascade face detector is no longer used, it is now remoed.
|
2020-03-22 14:14:26 +01:00 |
|
Emiliana
|
c03e222a49
|
Smaller, faster and better detection model.
|
2020-03-22 13:47:55 +01:00 |
|
Emiliana
|
a10eacc670
|
A new, custom face detection model is now used to lock onto faces for tracking.
|
2020-03-22 00:34:34 +01:00 |
|
Emiliana
|
4f611997f3
|
Fudging thresholds when the head turns left or right is cheating, but it seems to work well.
|
2020-03-08 18:15:43 +01:00 |
|