Bot releases are hidden (Show)
Changed the gaze tracking model to always run single threaded.
Published by emilianavt about 3 years ago
Fixed various issues, made other small improvements and added a new, experimental tracking model with improved wink support.
Published by emilianavt almost 4 years ago
Fixed some bugs.
Published by emilianavt almost 4 years ago
Reduced the impact of eye blinks and jaw movement on head pose estimation and fixed various things.
Published by emilianavt almost 4 years ago
This release contains various fixes and adjustments as well as two new tracking models with different quality and speed tradeoffs.
Published by emilianavt about 4 years ago
This release adds support for jaw bone animation to OpenSeeVRMDriver
, dynamic port selection support to OpenSeeLauncher
and updates the binary build of the face tracker to use onnxruntime 1.5.1, fixing some performance issues caused by the tracker not respecting thread limits.
Published by emilianavt about 4 years ago
This release decodes landmarks from the python side again, as somehow using the decoded landmarks from setting inference=True
on the models caused some issues
Published by emilianavt about 4 years ago
With this release, the landmark models decode landmarks within the ONNX models again. The included binary should run with lower CPU utilization at the same speed when enabling multithreading.
Published by emilianavt about 4 years ago
This release fixes a bug with the OpenSeeLauncher
and adds support for selecting device capability lines for direct show cameras and a --benchmark
option.
Published by emilianavt about 4 years ago
The main new feature with this release is a very fast, less accurate thirty point tracking model that can be activated with --model -1
.
Published by emilianavt about 4 years ago
This release contains bug fixes and mostly small improvements. It also contains an optional, simplified expression detection method.
Published by emilianavt about 4 years ago
Further reliability improvements. Landmark decoding has been moved from the ONNX model back into tracker.py
in one of the recent releases, but model.py
still contains suitable decoding code for exporting your own ONNX model containing the landmark decoding.
Published by emilianavt about 4 years ago
Improved reliability and logging.
Published by emilianavt about 4 years ago
This release includes various small optimizations that can lead to a 20-25% performance gain under certain conditions.
Published by emilianavt about 4 years ago
This release fixes further issues with the new camera code.
Published by emilianavt about 4 years ago
This release accumulates a lot of random changes, mainly to the Unity parts. One big change is that escapi is no longer used for webcam reading on Windows and has been replaced with libdshowcamera, which is also used in OBS.
Published by emilianavt over 4 years ago
This release introduces a new model for --model 2
. Unity components relying on 3D points will now skip frames with very bad 3D fits.
Published by emilianavt over 4 years ago
This release contains various improvements, such as improved models for --model 0
and --model 1
.
Published by emilianavt over 4 years ago
The main new feature of this release is a new default face detection model that is used to lock onto yet untracked faces for tracking. There are also some other small changes and fixes. The chin tracking point is used for fitting the 3D points once more to prevent the solvePnP
function from choosing an upside down fit.
Published by emilianavt over 4 years ago
New in this version:
OpenSeeVRMDriver
can now animate mouth and eyes using the face tracking information.OpenSeeVRMDriver
supports global hotkeys to override expressions.