hysts/ptgaze-mpiifacegaze-resnet-simple

ptgaze MPIIFaceGaze model (resnet_simple)

Appearance-based gaze estimation model used by the mpiifacegaze mode of ptgaze. It takes a normalized full-face image and predicts the gaze direction as pitch and yaw angles in the normalized space, following Zhang et al. (ETRA 2018 normalization; full-face model, CVPRW 2017).

Model details

• Architecture: truncated ResNet-18 backbone (first three stages) with a spatial-weights head, defined in ptgaze/models/mpiifacegaze/resnet_simple.py
• Input: 3x224x224 normalized face image (BGR channel order, ImageNet mean/std normalization)
• Output: gaze (pitch, yaw) in the normalized camera space
• Training code: hysts/pytorch_mpiigaze (listed as ResNet-14 there)
• Format: safetensors, converted from the original .pth checkpoint with ptgaze-convert (tensor-identical). The file metadata records mode: MPIIFaceGaze and model: resnet_simple.

The input normalization must match the conventions the training labels were generated with. See the notes on data normalization in the demo README.

Accuracy

Mean test angle error of 4.83 degrees with leave-one-person-out evaluation on MPIIFaceGaze (from the training repo results).

Usage

pip install ptgaze
ptgaze --mode mpiifacegaze

The demo downloads this file automatically. To inspect the weights directly:

from safetensors.torch import load_file

state_dict = load_file("model.safetensors")

Training data

This model was trained on the MPIIFaceGaze dataset, which is distributed under CC BY-NC-SA 4.0 (non-commercial). The model was trained for research purposes.

The dataset license binds the dataset recipient; it does not automatically extend to users of these weights. However, the legal status of model weights trained on datasets with restrictive terms is not settled. If you intend to use this model commercially, assess that risk yourself.

License

MIT, the same license as the ptgaze code (see the LICENSE file in this repository). The license covers the rights the author holds in these weights; see the Training data section above for the terms of the dataset they were trained on.

Citation

If you use this model, please cite the dataset paper:

Zhang, Xucong, Yusuke Sugano, Mario Fritz, and Andreas Bulling. "It's Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation." Proc. of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017. arXiv:1611.08860