| dkulon/hand-reconstruction |
66 |
|
0 |
0 |
about 6 years ago |
0 |
|
1 |
other |
Jupyter Notebook |
| Single Image 3D Hand Reconstruction with Mesh Convolutions |
| facebookresearch/VCMeshConv |
56 |
|
0 |
0 |
over 4 years ago |
0 |
|
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. |
| goodok/fastai_sparse |
42 |
|
0 |
1 |
over 5 years ago |
6 |
November 02, 2020 |
1 |
mit |
Jupyter Notebook |
| 3D augmentation and transforms of 2D/3D sparse data, such as 3D triangle meshes or point clouds in Euclidean space. Extension of the Fast.ai library to train Sub-manifold Sparse Convolution Networks |
| kuixu/3ddensenet.torch |
37 |
|
0 |
0 |
over 8 years ago |
0 |
|
0 |
|
Lua |
| 3D DenseNet(torch version) for ModelNet40 dataset |
| sw-gong/spiralnet_plus |
37 |
|
0 |
0 |
about 6 years ago |
0 |
|
0 |
mit |
Python |
| The project is an official implementation of our paper "SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator" (ICCV-W 2019) |
| papagina/MeshConvolution |
30 |
|
0 |
0 |
over 3 years ago |
0 |
|
5 |
mit |
Python |
| Code for Mesh Convolution Using a Learned Kernel Basis |
| adrienPoulenard/MDGCNN |
13 |
|
0 |
0 |
about 7 years ago |
0 |
|
2 |
|
C++ |
| Multi Directional Geodesic Convolutional Neural Networks |
| karthisugumar/CSE240D-Hierarchical_Mesh_NoC-Eyeriss_v2 |
7 |
|
0 |
0 |
over 6 years ago |
0 |
|
0 |
|
SystemVerilog |
| A SystemVerilog implementation of Row-Stationary dataflow and Hierarchical Mesh Network-on-Chip Architecture based on Eyeriss CNN Accelerator |
