How to get 3D mesh from your model's output? about nonlinear_face_3dmm HOT 15 OPEN

The author adopted the Basel Face Model (BFM) facial mesh triangle topology as stated in his paper. @HOMGH
the problem is that I'm getting always the same 3D mesh for each input (the below 3D mesh). It seems I'm getting the mean shape!

Hi, @HOMGH Can you share the code for outputing 3D face mesh? thank you very much!
The part of the code which is used to generate 3D mesh is :
write_obj_with_colors(('./test' '.obj'), vertices_in, trian.T, colors_in) #save 3d face(can open with meshlab)
in which the inputs are as follows:
trian= load_3DMM_tri_reduce() or load_3DMM_tri()
colors_in = np.ones((VERTEX_NUM_REDUCE,3)) (if you just want to display textureless 3D mesh)
vertices_in = np.reshape(verti,(VERTEX_NUM_REDUCE,3)) (this is the vertices output of network)

The write_obj_with_colors function can be found in write.py file:

def  write_obj_with_colors(obj_name, vertices, triangles, colors):
    ''' Save 3D face model with texture represented by colors.
    Args:
        obj_name: str
        vertices: shape = (nver, 3)
        colors: shape = (nver, 3)
        triangles: shape = (ntri, 3)
    '''
    triangles = triangles.copy()
    triangles += 1 # meshlab start with 1
    
    if obj_name.split('.')[-1] != 'obj':
        obj_name = obj_name + '.obj'
        
    # write obj
    with open(obj_name, 'w') as f:
        
        # write vertices & colors
        for i in range(vertices.shape[0]):
            # s = 'v {} {} {} \n'.format(vertices[0,i], vertices[1,i], vertices[2,i])
            s = 'v {} {} {} {} {} {}\n'.format(vertices[i, 0], vertices[i, 1], vertices[i, 2], colors[i, 0], colors[i, 1], colors[i, 2])
            f.write(s)

        # write f: ver ind/ uv ind
        [k, ntri] = triangles.shape
        for i in range(triangles.shape[0]):
            # s = 'f {} {} {}\n'.format(triangles[i, 0], triangles[i, 1], triangles[i, 2])
            s = 'f {} {} {}\n'.format(triangles[i, 2], triangles[i, 1], triangles[i, 0])
            f.write(s)

from nonlinear_face_3dmm.

Hello, did you manage to create? I have been meaning to do the same thing

from nonlinear_face_3dmm.

Hello, did you manage to create? I have been meaning to do the same thing

No I couldn't get the correct 3D mesh. This is what I got:

from nonlinear_face_3dmm.

Did you use the generated txt to create the model? And there is no texture?

from nonlinear_face_3dmm.

Did you use the generated txt to create the model? And there is no texture?

For now, I just want to display the shape. with no texture.

from nonlinear_face_3dmm.

And how did you create this mesh?

from nonlinear_face_3dmm.

And how did you create this mesh?

I used write_obj_with_colors(('./test' '.obj'), vertices_in, tri_in, colors_in) #save 3d face(can open with meshlab).
vertices is the generated shape vertices. But I'm not sure about triangle. I used load_3DMM_tri_reduce() function, but it seems something is wrong! Any idea?

from nonlinear_face_3dmm.

Is this function available on this git repository, I did not find it in here. Is it from another repository? And I have no idea how to estimate the triangles.

from nonlinear_face_3dmm.

The author adopted the Basel Face Model (BFM) facial mesh triangle topology as stated in his paper. @HOMGH

from nonlinear_face_3dmm.

The author adopted the Basel Face Model (BFM) facial mesh triangle topology as stated in his paper. @HOMGH
the problem is that I'm getting always the same 3D mesh for each input (the below 3D mesh). It seems I'm getting the mean shape!

from nonlinear_face_3dmm.

The author adopted the Basel Face Model (BFM) facial mesh triangle topology as stated in his paper. @HOMGH
the problem is that I'm getting always the same 3D mesh for each input (the below 3D mesh). It seems I'm getting the mean shape!

Hi,@HOMGH Can you share the code for outputting 3D face mesh? thank you very much!

from nonlinear_face_3dmm.

The author adopted the Basel Face Model (BFM) facial mesh triangle topology as stated in his paper. @HOMGH
the problem is that I'm getting always the same 3D mesh for each input (the below 3D mesh). It seems I'm getting the mean shape!

Hi, @HOMGH Can you share the code for outputing 3D face mesh? thank you very much!

from nonlinear_face_3dmm.

The author adopted the Basel Face Model (BFM) facial mesh triangle topology as stated in his paper. @HOMGH
the problem is that I'm getting always the same 3D mesh for each input (the below 3D mesh). It seems I'm getting the mean shape!

Hi, @HOMGH Can you share the code for outputing 3D face mesh? thank you very much!
The part of the code which is used to generate 3D mesh is :
write_obj_with_colors(('./test' '.obj'), vertices_in, trian.T, colors_in) #save 3d face(can open with meshlab)
in which the inputs are as follows:
trian= load_3DMM_tri_reduce() or load_3DMM_tri()
colors_in = np.ones((VERTEX_NUM_REDUCE,3)) (if you just want to display textureless 3D mesh)
vertices_in = np.reshape(verti,(VERTEX_NUM_REDUCE,3)) (this is the vertices output of network)

The write_obj_with_colors function can be found in write.py file:

def  write_obj_with_colors(obj_name, vertices, triangles, colors):
    ''' Save 3D face model with texture represented by colors.
    Args:
        obj_name: str
        vertices: shape = (nver, 3)
        colors: shape = (nver, 3)
        triangles: shape = (ntri, 3)
    '''
    triangles = triangles.copy()
    triangles += 1 # meshlab start with 1
    
    if obj_name.split('.')[-1] != 'obj':
        obj_name = obj_name + '.obj'
        
    # write obj
    with open(obj_name, 'w') as f:
        
        # write vertices & colors
        for i in range(vertices.shape[0]):
            # s = 'v {} {} {} \n'.format(vertices[0,i], vertices[1,i], vertices[2,i])
            s = 'v {} {} {} {} {} {}\n'.format(vertices[i, 0], vertices[i, 1], vertices[i, 2], colors[i, 0], colors[i, 1], colors[i, 2])
            f.write(s)

        # write f: ver ind/ uv ind
        [k, ntri] = triangles.shape
        for i in range(triangles.shape[0]):
            # s = 'f {} {} {}\n'.format(triangles[i, 0], triangles[i, 1], triangles[i, 2])
            s = 'f {} {} {}\n'.format(triangles[i, 2], triangles[i, 1], triangles[i, 0])
            f.write(s)

Hi, @HOMGH Thank you so much for replying to me so quickly。
I have another question. Where should the code you share be added to the model file? Can you give me some tips? Thank you very much for sharing and look forward to hearing from you.

Hi, I want to ask what does "trian.T" in the red box mean above image?
Is it convenient to contact you by email? My email address is "[email protected]". Looking forward to your reply.

from nonlinear_face_3dmm.

Hello, did you manage to create? I have been meaning to do the same thing

No I couldn't get the correct 3D mesh. This is what I got:

Hi，@HOMGH can you share code of the G_loss_frecon for me ? Thank you.

from nonlinear_face_3dmm.

The author adopted the Basel Face Model (BFM) facial mesh triangle topology as stated in his paper. @HOMGH
the problem is that I'm getting always the same 3D mesh for each input (the below 3D mesh). It seems I'm getting the mean shape!

Hi, @HOMGH Can you share the code for outputing 3D face mesh? thank you very much!
The part of the code which is used to generate 3D mesh is :
write_obj_with_colors(('./test' '.obj'), vertices_in, trian.T, colors_in) #save 3d face(can open with meshlab)
in which the inputs are as follows:
trian= load_3DMM_tri_reduce() or load_3DMM_tri()
colors_in = np.ones((VERTEX_NUM_REDUCE,3)) (if you just want to display textureless 3D mesh)
vertices_in = np.reshape(verti,(VERTEX_NUM_REDUCE,3)) (this is the vertices output of network)

The write_obj_with_colors function can be found in write.py file:

def  write_obj_with_colors(obj_name, vertices, triangles, colors):
    ''' Save 3D face model with texture represented by colors.
    Args:
        obj_name: str
        vertices: shape = (nver, 3)
        colors: shape = (nver, 3)
        triangles: shape = (ntri, 3)
    '''
    triangles = triangles.copy()
    triangles += 1 # meshlab start with 1
    
    if obj_name.split('.')[-1] != 'obj':
        obj_name = obj_name + '.obj'
        
    # write obj
    with open(obj_name, 'w') as f:
        
        # write vertices & colors
        for i in range(vertices.shape[0]):
            # s = 'v {} {} {} \n'.format(vertices[0,i], vertices[1,i], vertices[2,i])
            s = 'v {} {} {} {} {} {}\n'.format(vertices[i, 0], vertices[i, 1], vertices[i, 2], colors[i, 0], colors[i, 1], colors[i, 2])
            f.write(s)

        # write f: ver ind/ uv ind
        [k, ntri] = triangles.shape
        for i in range(triangles.shape[0]):
            # s = 'f {} {} {}\n'.format(triangles[i, 0], triangles[i, 1], triangles[i, 2])
            s = 'f {} {} {}\n'.format(triangles[i, 2], triangles[i, 1], triangles[i, 0])
            f.write(s)

What is the vertices_in? Do you mean the output 'pred_shape.txt' ? Many thanks.

from nonlinear_face_3dmm.