img2pose EU AI Act Compliance Profile

img2pose

Model Description

img2pose uses Faster R-CNN to predict 6 Degree of Freedom Pose (DoF) for all faces in the photo. An interesting property of this model is that it can project the 3D face onto a 2D plane to also identify bounding boxes for each face. It does not require any other face detection model.

Model Details

• Model Type: Convolutional Neural Network (CNN)
• Architecture: Faster R-CNN
• Framework: PyTorch

Model Sources

• Repository: GitHub Repository
• Paper: img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation

Citation

If you use this model in your research or application, please cite the following paper:

Vítor Albiero, Xingyu Chen, Xi Yin, Guan Pang, Tal Hassner, "img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation," CVPR, 2021, arXiv:2012.07791

Acknowledgements

We thank Albiero Vítor for sharing their code and training weights with a permissive license.

Example Useage

import numpy as np
import os
import json
import torch
import torch.nn as nn
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
from feat.facepose_detectors.img2pose.deps.models import FasterDoFRCNN, postprocess_img2pose
from feat.utils.io import get_resource_path
from torchvision.models.detection.backbone_utils import resnet_fpn_backbone


# Load Model Configurations
facepose_config_file = hf_hub_download(repo_id= "py-feat/img2pose", filename="config.json", cache_dir=get_resource_path())
with open(facepose_config_file, "r") as f:
    facepose_config = json.load(f)
           
# Initialize

Your obligations as a img2pose deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Library