You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -35,9 +35,9 @@ Our results are obtained on the 483 × 724 pixels resolution of the original ima
35
35
*SMPL-X* (SMPL eXpressive) is a unified body model with shape parameters trained jointly for the
36
36
face, hands and body. *SMPL-X* uses standard vertex based linear blend skinning with learned corrective blend
37
37
shapes, has N = 10, 475 vertices and K = 54 joints,
38
-
which includes joints for the neck, jaw, eyeballs and fingers.
39
-
SMPL-X is defined by a function M(θ, β, ψ), where θ is the pose parameter, β the shape parameter and
40
-
ψ the expression parameter.
38
+
which include joints for the neck, jaw, eyeballs and fingers.
39
+
SMPL-X is defined by a function M(θ, β, ψ), where θ is the pose parameters, β the shape parameters and
40
+
ψ the facial expression parameters.
41
41
42
42
43
43
## Installation
@@ -55,22 +55,22 @@ python setup.py install
55
55
56
56
## Downloading the model
57
57
58
-
To download the *SMPL-X* go to the [project website](https://smpl-x.is.tue.mpg.de/) and register to get access to the downloads section.
58
+
To download the *SMPL-X*model go to the [project website](https://smpl-x.is.tue.mpg.de/) and register to get access to the downloads section.
59
59
60
-
## Loading SMPL-X, SMPL-H and SMPL
60
+
## Loading SMPL-X, SMPL+H and SMPL
61
61
62
-
### SMPL and SMPL-H setup
62
+
### SMPL and SMPL+H setup
63
63
64
-
Depending on the model you want to use, please follow the respective download instructions. To switch between SMPL, SMPL-H and SMPL-X just change the *model_path* or *model_type* parameters. For more details check the docs of the model classes.
65
-
Before using SMPL and SMPL-H you should follow the instructions in [tools/README.md](./tools/README.md) to remove the
66
-
Chumpy objects from both model pkls, as well as merge the MANO parameters with SMPL-H.
64
+
The loader gives the option to use any of the SMPL-X, SMPL+H and SMPL models. Depending on the model you want to use, please follow the respective download instructions. To switch between SMPL, SMPL+H and SMPL-X just change the *model_path* or *model_type* parameters. For more details please check the docs of the model classes.
65
+
Before using SMPL and SMPL+H you should follow the instructions in [tools/README.md](./tools/README.md) to remove the
66
+
Chumpy objects from both model pkls, as well as merge the MANO parameters with SMPL+H.
67
67
68
68
### Model loading
69
69
70
70
You can either use the [create](https://github.com/vchoutas/smplx/blob/c63c02b478c5c6f696491ed9167e3af6b08d89b1/smplx/body_models.py#L54)
71
71
function from [body_models](./smplx/body_models.py) or directly call the constructor for the
[SMPL-H](https://github.com/vchoutas/smplx/blob/c63c02b478c5c6f696491ed9167e3af6b08d89b1/smplx/body_models.py#L395) and
73
+
[SMPL+H](https://github.com/vchoutas/smplx/blob/c63c02b478c5c6f696491ed9167e3af6b08d89b1/smplx/body_models.py#L395) and
74
74
[SMPL-X](https://github.com/vchoutas/smplx/blob/c63c02b478c5c6f696491ed9167e3af6b08d89b1/smplx/body_models.py#L628) model. The path to the model can either be the path to the file with the parameters or a directory with the following structure:
75
75
```bash
76
76
models
@@ -100,7 +100,7 @@ script to visualize the results. For this step you have to install the [pyrender
100
100
101
101
## Citation
102
102
103
-
If you find this code useful in your research then please cite:
103
+
If you find this Model & Software useful in your research we would kindly ask you to cite:
0 commit comments