Pretrained models and datasets of our method SemiUHPE
Title: Semi-Supervised Unconstrained Head Pose Estimation in the Wild
Paper link: https://arxiv.org/abs/2404.02544
Code link: https://github.com/hnuzhy/SemiUHPE
Project link: https://hnuzhy.github.io/projects/SemiUHPE/
Pretrained models
- Labeled DAD3DHeads + Unlabeled COCOHead (based on ResNet50): DAD-COCOHead-ResNet50-best.pth
- Labeled DAD3DHeads + Unlabeled COCOHead (based on RepVGG): DAD-COCOHead-RepVGG-best.pth
- Labeled DAD3DHeads + Unlabeled COCOHead (based on EffNetV2-S): DAD-COCOHead-EffNetV2-S-best.pth
- Labeled DAD3DHeads + Unlabeled WildHead (based on EffNetV2-S): DAD-WildHead-EffNetV2-S-best.pth
Processed datasets
Unlabeled WildHead (the combination of COCOHead, CrowdHuman and OpenImageV6 with totally about 403K heads):
- You can download our ready-made zip file WildHead_30.zip.
Unlabeled COCOHead (extracted heads from COCO train2017 and val2017 with totally about 74K heads):
- All head images are extracted from COCO, and head bboxes are from HumanParts. Please see dataset_COCOHead.py for more details.
Unlabeled CrowdHuman (extracted heads from CrowdHuman train-set and val-set with totally about 163K heads):
- All head images are extracted from CrowdHuman, and head bboxes are from BFJDet. Please see dataset_CrowdHuman.py for more details.
Unlabeled OpenImageV6 (extracted heads from OpenImageV6 train-set, val-set and test-set with totally about 166K heads):
- All head images are extracted from OpenImageV6. You can download all head-related images by using FiftyOne. Then you can process them by using headcrop_OpenImageV6.py
Labeled 300W-LP and AFLW2000 (about 120K synthetic heads in 300W-LP, and 2000 real wild heads in AFLW2000):
- You can download them from 3DDFA homepage. Please see dataset_300WLP.py and dataset_AFLW2000.py for more details.
Labeled DAD-3DHeads (37840 images in train-set, 4312 images in val-set, and 2746 images in test-set):
- You can download them from DAD-3DHeads. Please see dataset_DAD3DHeads.py for more details.