Project Name | Stars | Downloads | Repos Using This | Packages Using This | Most Recent Commit | Total Releases | Latest Release | Open Issues | License | Language |
---|---|---|---|---|---|---|---|---|---|---|
Face Aging Caae | 497 | 5 years ago | 33 | Python | ||||||
Age Progression/Regression by Conditional Adversarial Autoencoder | ||||||||||
Pointnet Autoencoder | 230 | 4 years ago | 12 | other | Python | |||||
Autoencoder for Point Clouds | ||||||||||
Singleviewreconstruction | 159 | 3 years ago | mit | Python | ||||||
Official Code: 3D Scene Reconstruction from a Single Viewport | ||||||||||
Deep_image_prior | 146 | 4 years ago | apache-2.0 | Python | ||||||
Image reconstruction done with untrained neural networks. | ||||||||||
Cnn Vae | 86 | 4 months ago | mit | Python | ||||||
Variational Autoencoder (VAE) with perception loss implementation in pytorch | ||||||||||
Video_predict | 75 | 2 years ago | 3 | mit | Python | |||||
LSTM sequence modeling of video data | ||||||||||
Hand Reconstruction | 66 | 4 years ago | 1 | other | Jupyter Notebook | |||||
Single Image 3D Hand Reconstruction with Mesh Convolutions | ||||||||||
Adversarial Autoencoder | 57 | 5 years ago | 5 | mit | Python | |||||
An adversarial autoencoder implementation in pytorch | ||||||||||
Vcmeshconv | 56 | 3 years ago | 4 | other | C++ | |||||
Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to capture fine-grained deformations. Furthermore, these methods can only be applied to a template-specific surface mesh, and is not applicable to more general meshes, like tetrahedrons and non-manifold meshes. While more general graph convolution methods can be employed, they lack performance in reconstruction precision and require higher memory usage. In this paper, we propose a non-template-specific fully convolutional mesh autoencoder for arbitrary registered mesh data. It is enabled by our novel convolution and (un)pooling operators learned with globally shared weights and locally varying coefficients which can efficiently capture the spatially varying contents presented by irregular mesh connections. Our model outperforms state-of-the-art methods on reconstruction accuracy. In addition, the latent codes of our network are fully localized thanks to the fully convolutional structure, and thus have much higher interpolation capability than many traditional 3D mesh generation models. | ||||||||||
Vae Pytorch | 46 | 7 years ago | Jupyter Notebook | |||||||
AE and VAE Playground in PyTorch |