Epipolar Transformers

notion image
Yihui He, Rui Yan, Katerina Fragkiadaki, Shoou-I Yu (Carnegie Mellon University, Facebook Reality Labs)
Oral presentation and human pose demo videos (playlist):
Video preview
Video preview


MPJPE (mm)
model & log
We also provide 2D to 3D lifting network implementations for these two papers:



Python 3, pytorch > 1.2+ and pytorch < 1.4
pip install -r requirements.txtconda install pytorch cudatoolkit=10.0 -c pytorch

Pretrained weights download

mkdir outscd datasets/bash get_pretrained_models.sh
Please follow the instructions in datasets/README.md for preparing the dataset


python main.py --cfg path/to/configtensorboard --logdir outs/


Testing with latest checkpoints
python main.py --cfg configs/xxx.yaml DOTRAIN False
Testing with weights
python main.py --cfg configs/xxx.yaml DOTRAIN False WEIGHTS xxx.pth


Epipolar Transformers Visualization

notion image
  • Download the output pkls for non-augmented models and extract under outs/
  • Make sure outs/epipolar/keypoint_h36m_fixed/visualizations/h36m/output_1.pkl exists.
  • Use scripts/vis_hm36_score.ipynb
    • To select a point, click on the reference view (upper left), the source view along with corresponding epipolar line, and the peaks for different feature matchings are shown at the bottom left.

Human 3.6M input visualization

notion image
python main.py --cfg configs/epipolar/keypoint_h36m.yaml DOTRAIN False DOTEST False EPIPOLAR.VIS True VIS.H36M True SOLVER.IMS_PER_BATCH 1 python main.py --cfg configs/epipolar/keypoint_h36m.yaml DOTRAIN False DOTEST False VIS.MULTIVIEWH36M True EPIPOLAR.VIS True SOLVER.IMS_PER_BATCH 1

Human 3.6M prediction visualization

Video preview
# generate images python main.py --cfg configs/epipolar/keypoint_h36m_zresidual_fixed.yaml DOTRAIN False DOTEST True VIS.VIDEO True DATASETS.H36M.TEST_SAMPLE 2 # generate images python main.py --cfg configs/benchmark/keypoint_h36m.yaml DOTRAIN False DOTEST True VIS.VIDEO True DATASETS.H36M.TEST_SAMPLE 2 # use https://github.com/yihui-he/multiview-human-pose-estimation-pytorch to generate images for ICCV 19 python run/pose2d/valid.py --cfg experiments-local/mixed/resnet50/256_fusion.yaml # set test batch size to 1 and PRINT_FREQ to 2 # generate video python scripts/video.py --src outs/epipolar/keypoint_h36m_fixed/video/multiview_h36m_val/

Citing Epipolar Transformers

If you find Epipolar Transformers helps your research, please cite the paper:
@inproceedings{epipolartransformers, title={Epipolar Transformers}, author={He, Yihui and Yan, Rui and Fragkiadaki, Katerina and Yu, Shoou-I}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={7779--7788}, year={2020} }


Please create a new issue: