TimoBolkart / voca

This codebase demonstrates how to synthesize realistic 3D character animations given an arbitrary speech signal and a static character mesh.

https://voca.is.tue.mpg.de/en

TimoBolkart/voca Issues

Hot to get blink_exp_betas for another flame version?
Updated 3 days ago
Missing data on subj_seq_to_idx.pkl file
Updated 10 days ago1
Where to download npy and pkl files
Updated a month ago1
dataset/voca_face_former/templates.pkl not found
Updated a month ago1
Inference other .ply files
Updated a month ago
has an _output_shapes attribute inconsistent with the GraphDef for output #3: Dimension 0 in both shapes must be equal, but are 0 and 1. Shapes are [0] and [1].
Updated a month ago8
is the eye blink useful for FLame 2020 model ?
Updated 4 months ago3
I haven't found the 'output_graph.pb' file, where can I get it?
Updated a year ago
How can I make npy and pkl training data for my own dataset?
Updated a year ago5
If I want to control the expression of the eyes, how should I set the parameters?
Updated a year ago
Unsolved reference tfbody
Updated a year ago
Training with new Tensorflow Version
Updated a year ago
Unknown mesh file format.
Closed a year ago1
Can I train this on custom dataset?
Updated a year ago
How to control expression in the edit_sequence.py?
Updated a year ago2
How could i get apple arkit 52 blendshapes?
Closed a year ago1
question about the learning rate decay
Closed a year ago1
Problem of training voca
Updated a year ago
not working Still!
Updated a year ago13
Initialization Of Decoder Layer
Updated a year ago
can you give pretrained_models？
Closed a year ago
Should --uv_template_fname be the same as --template_fname in run_voca.py?
Updated a year ago
Windows support and installing MPI-IS / mesh
Updated a year ago1
"video.mp4" only has speech but no images ?
Updated 2 years ago4
Missing files from training data
Updated 2 years ago3
What's the best way to render the output meshes in Blender?
Updated 2 years ago1
Which equipment is needed to collect data and how can I buy it?
Closed 2 years ago3
Difference between generic FLAME models and VOCA-compatible FLAME models?
Closed 2 years ago10
Is it possible to map the face mesh to a depth map?
Closed 2 years ago1
How manually control expression ??
Closed 2 years ago1
Are vertices used in training regular vertices or transformed vertices?
Closed 2 years ago2
Can't find "output_graph.pb" or "gstep_52280.model" in trained model
Updated 2 years ago
Flame model pose explanation
Closed 2 years ago1
Assign random shape parameters
Closed 2 years ago2
Is it possible to map facial models to BlendShape?
Closed 2 years ago1
win10 system problem:voca-master\FLAME_eye_blink\tmp9_oymmsq.mp4: No such file or directory
Updated 2 years ago5
VOCA on CPU's & Time history of Mesh
Updated 2 years ago
Training VOCA question
Updated 2 years ago2
Following this way： “After unposing， For each sequence, the neck boundary and the ears are automatically fixed”, but I got mesh which neck and ears are not fixed. Are there some problem for my unpose method?
Closed 2 years ago
How to convert model into pb file which can be used in C?
Closed 3 years ago2
Interpertation of %M in the camera calibration files
Closed 2 years ago4
The training data is not downloadable, please check it
Closed 3 years ago3
raise KeyError("The name %s refers to a Tensor which does not " KeyError: "The name 'deepspeech/input_node:0' refers to a Tensor which does not exist. The operation, 'deepspeech/input_node', does not exist in the graph."
Closed 3 years ago3
Excuse me, what does the output folder animation_output-->meshes means?
Closed 3 years ago1
Rendering Error on Centos Server With Tensorflow-ROCm version
Updated 3 years ago1
How do I use with python
Closed 3 years ago1
result video flickering problem!
Closed 3 years ago3
NOt working
Closed 3 years ago2
VOCA trainingSet format
Updated 3 years ago
Run the demo in Windows environment
Closed 3 years ago