├── S2D.rar
├── Motion3DGAN.rar
└── README.md


/S2D.rar:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CRISTAL-3DSAM/Sparse2Dense/HEAD/S2D.rar


--------------------------------------------------------------------------------
/Motion3DGAN.rar:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CRISTAL-3DSAM/Sparse2Dense/HEAD/Motion3DGAN.rar


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Sparse2dense: Sparse to Dense Dynamic 3D Facial Expression Generation
 2 | 
 3 | This is an official repository of the paper Sparse to Dense Dynamic 3D Facial Expression Generation. https://arxiv.org/abs/2105.07463
 4 | 
 5 | 
 6 | # Results
 7 | 
 8 | - 4D Facial expression generation
 9 |  
10 | ![tst_githubvideo_4](https://user-images.githubusercontent.com/19242829/158143735-a38fece3-75ed-4d4e-b873-bb167624c846.gif)
11 | 
12 | 
13 | - Interpolation between 4D facial expressions 
14 |  
15 | ![tst_githubvideo_2](https://user-images.githubusercontent.com/19242829/158142211-174651ec-0f46-4ebd-8a3d-0564f24b77a4.gif)
16 | ![tst_githubvideo_3](https://user-images.githubusercontent.com/19242829/158142959-7887841e-8a48-43d1-9f07-9371af8cbb09.gif)
17 | 
18 | - Speech transfer 
19 | 
20 | ![tst_githubvideo](https://user-images.githubusercontent.com/19242829/158222004-abf2e76b-362e-48e8-b859-aa5fb4070234.gif)
21 | 
22 | 
23 | # Usage
24 | The code is divided into two folders: 
25 | 
26 | Motion3DGAN: used to train a GAN generator of 3D landmarks motion;
27 | 
28 | S2D: used to train and test the decoder that deforms the 3D mesh according to a given landmarks configuration;
29 | 
30 | You will find a Readme file inside each one of these folders with the installation and the usage instructions.
31 | 
32 | # Models
33 | Please download models from the link below and include them in S2D\Models folder.
34 | 
35 | https://drive.google.com/drive/folders/1-RdBhUfP7JcxihVCT4AdLRYfSBOD9Rmq?usp=sharing
36 | 
37 | # Acknowledgments
38 | This work was supported by the French State, managed
39 | by National Agency for Research (ANR) National Agency
40 | for Research (ANR) under the Investments for the future
41 | program with reference ANR-16-IDEX-0004 ULNE and
42 | by the ANR project Human4D ANR-19-CE23-0020. This
43 | paper was also partially supported by European Union’s
44 | Horizon 2020 research and innovation program under grant
45 | number 951911 - AI4Media.
46 | 
47 | # Reference
48 | Please cite the following paper if you use the code directly or indirectly in your research/projects.
49 | 
50 | <div class="snippet-clipboard-content position-relative overflow-auto" data-snippet-clipboard-copy-content="@inproceedings{otberdout2022sparse,
51 | title = {Sparse to Dense Dynamic 3D Facial Expression Generation},
52 | author = {Otberdout, Naima and Ferrari, Claudio and Daoudi, Mohamed and Berritti, Stefano and Del Bimbo, Alberto},
53 | booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
54 | month = jun,
55 | year = {2022},
56 | }"><pre><code>@inproceedings{otberdout2022sparse,
57 | title = {Sparse to Dense Dynamic 3D Facial Expression Generation},
58 | author = {Otberdout, Naima and Ferrari, Claudio and Daoudi, Mohamed and Berritti, Stefano and Del Bimbo, Alberto},
59 | booktitle = {Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
60 | month = jun,
61 | year = {2022},
62 | }
63 | 


--------------------------------------------------------------------------------