![]() Creatively combining 3D models, rapidly producing 3D models from images, and creating synthetic data for other machine learning applications and simulations are just a handful of the myriad use cases for 3D model generation. A particularly hot subfield is the generation of 3D models. For TensorFlow users, there is also TensorFlow Graphics. ![]() For PyTorch users looking to try some 3D deep learning themselves, the Kaolin library is worth looking into. If you are interested in the subject, take a look. There is a burgeoning field of deep learning research focused on applying DL techniques to 3D geomet ry and computer graphics applications, as evidenced by this lengthy collection of recent research. (Figure 6 in paper) Image conditional samples (yellow) generated using nucleus sampling with top-p=0.9 and ground truth meshes (blue).
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |