| timzhang642/3D-Machine-Learning |
8,647 |
|
0 |
0 |
about 3 years ago |
0 |
|
19 |
|
|
| A resource repository for 3D machine learning |
| charlesq34/pointnet |
4,396 |
|
0 |
0 |
over 2 years ago |
0 |
|
176 |
other |
Python |
| PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation |
| NVIDIAGameWorks/kaolin |
4,038 |
|
0 |
0 |
over 2 years ago |
3 |
May 03, 2023 |
144 |
apache-2.0 |
Python |
| A PyTorch Library for Accelerating 3D Deep Learning Research |
| google-research-datasets/Objectron |
1,958 |
|
0 |
0 |
over 3 years ago |
0 |
|
21 |
other |
Jupyter Notebook |
| Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes |
| google/nerfies |
1,459 |
|
0 |
0 |
about 2 years ago |
0 |
|
36 |
apache-2.0 |
Python |
| This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies. |
| hustvl/4DGaussians |
1,243 |
|
0 |
0 |
over 2 years ago |
0 |
|
26 |
other |
Jupyter Notebook |
| 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering |
| ranahanocka/MeshCNN |
1,211 |
|
0 |
0 |
about 4 years ago |
0 |
|
76 |
mit |
Python |
| Convolutional Neural Network for 3D meshes in PyTorch |
| google/hypernerf |
847 |
|
0 |
0 |
about 2 years ago |
0 |
|
32 |
apache-2.0 |
Python |
| Code for "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields". |
| FORTH-ModelBasedTracker/MocapNET |
738 |
|
0 |
0 |
over 2 years ago |
0 |
|
16 |
other |
C++ |
| We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance |
| astorfi/3D-convolutional-speaker-recognition |
634 |
|
0 |
0 |
about 6 years ago |
0 |
|
7 |
apache-2.0 |
Python |
| :speaker: Deep Learning & 3D Convolutional Neural Networks for Speaker Verification |
