Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Estimate 3D face pose (6DoF) or 11 parameters of 3x4 projection matrix by a Convolutional Neural Network
| Date | Stars |
|---|---|
| 2026-07-31 | 509 |
| 2026-08-03 | 509 |
| 2026-08-04 | 509 |
| 2026-08-06 | 509 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Face-Pose-Net  <sub>**Extreme face alignment examples:** Faces rendered to a 45 degrees yaw angle (aligned to half profile) using our FacePoseNet. Images were taken from the IJB-A collection and represent extreme viewing conditions, including near profile views, occlusions, and low resolution. Such conditions are often too hard for existing face landmark detection methods to handle yet easily aligned with our FacePoseNet.</sub> <br/> <br/> This page contains DCNN model and python code to robustly estimate 6 degrees of freedom, 3D face pose from an unconstrained image, without the use of face landmark detectors. The method is described in the paper: _F.-J. Chang, A. Tran, T. Hassner, I. Masi, R. Nevatia, G. Medioni, "[FacePoseNet: Making a Case for Landmark-Free Face Alignment](https://arxiv.org/abs/1708.07517)", in 7th IEEE International Workshop on Analysis and Modeling of Faces and Gestures, ICCV Workshops, 2017_ [1]. This release bundles up our **FacePoseNet** (FPN) with the **Face Renderer** from Masi _et al._ [2,5], which is available separately from [this project page](https://github.com/iacopomasi/face_specific_augm). The result is an end-to-end pipeline that seamlessly estimates facial pose and produces multiple rendered views to be used for face alignment and data augmentation.  ## Updates (Modified and New features, 12/20/2018) * FPN structure is changed to ResNet-101 for better pose prediction [fpn-resnet101](./ResNet/ThreeDMM_shape.py) * **Two versions of FPNs (under the assumption of weak perspective transformation) are added**: * (1) **Predict 6DoF head pose** (scale, pitch, yaw, roll, translation_x, translation_y): [main_predict_6DoF.py](./main_predict_6DoF.py) * (2) **Predict 11 parameters of the 3x4 projection matrix**: [main_predict_ProjMat.py](./main_predict_ProjMat.py) * The codes to convert 6DoF head pose to 3x4 projection matrix is [here](https://github.com/fengju514/Face-Pose-Net/blob/fb733f358d9f633f6525a41f3a7a0a99e5c71647/main_predict_6DoF.py#L263-L268) * The codes to convert 11 parameters / 3x4 projection matrix to 6DoF head pose is [here](https://github.com/fengju514/Face-Pose-Net/blob/92bd65fa056d17065890e186ca2f2b376a5ab135/main_predict_ProjMat.py#L306-L308) * The corresponding 3D shape and landmarks can be obtained by predicted 6DoF head pose [3D shape from 6DoF](https://github.com/fengju514/Face-Pose-Net/blob/92bd65fa056d17065890e186ca2f2b376a5ab135/main_predict_6DoF.py#L271-L297) or by predicted 11 parameters [3D shape from 11 parameters](https://github.com/fengju514/Face-Pose-Net/blob/92bd65fa056d17065890e186ca2f2b376a5ab135/main_predict_ProjMat.py#L272-L297) * Download new FPN models: Please put all model files [here](https://www.dropbox.com/sh/lr9u4my1qrhmgik/AADQVUIHSJIUXqUAj1AoZMIGa?dl=0) in the folder `models` * Download BFM models: Please put BFM shape and expression files [here](https://www.dropbox.com/sh/ru7ierl9516a9az/AABTP9hJj3dJnapicFFgHmOna?dl=0) in the folder `BFM` * Run new FPN to predict 6DoF head pose: ```bash $ python main_predict_6DoF.py <gpu_id> <input-list-path> ``` * Run new FPN to predict 11DoF parameters of the projection matrix: ```bash $ python main_predict_ProjMat.py <gpu_id> <input-list-path> ``` We provide a sample input list available [here](./input_list.txt). ```bash <FILE_NAME, FACE_X, FACE_y, FACE_WIDTH, FACE_HEIGHT> ``` where `<FACE_X, FACE_y, FACE_WIDTH, FACE_HEIGHT>` is the x,y coordinates of the upper-left point, the width, and the height of the tight face bounding box, either obtained manually, by the face detector or by the landmark detector. The predicted 6DoF and 11DoF results would be saved in [output_6DoF folder](https://github.com/fengju514/Face-Pose-Net/blob/a7923b764f92892021297fd046065c22a41dc519/main_predict_6DoF.py#L232-L236) and [output_ProjMat folder](https://github.com/fengju514/Face-Pose-Net/blob/a7923b764f92892021297fd046065c22a41dc519/main_predict_ProjMat.py#
Excerpt of 9,244 characters
Read on GitHub
99
Iacopo Masi · Sapienza, University of Rome · United States
16
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d6beb6e0802558cf, topic:pose-estimation, topic:face-recognition