3D-Human-Pose-Perception-from-Egocentric-Stereo-Videos (CVPR 2024)

Official PyTorch inference code of our CVPR 2024 paper, "3D Human Pose Perception from Egocentric Stereo Videos".

For any questions, please contact the first author, Hiroyasu Akada [hakada@mpi-inf.mpg.de] .

[Project Page] [Benchmark Challenge]

Citation

    @inproceedings{hakada2024unrealego2,
      title = {3D Human Pose Perception from Egocentric Stereo Videos},
      author = {Akada, Hiroyasu and Wang, Jian and Golyanik, Vladislav and Theobalt, Christian},
      booktitle = {Computer Vision and Pattern Recognition (CVPR)},
      year = {2024}
    }

UnrealEgo2/UnrealEgo-RW Datasets

Download

You can download the UnrealEgo2/UnrealEgo-RW datasets on our benchmark challenge page.

Depths from SfM/Metashape

You can donwload depth data from SfM/Metashape described in our paper.

• Depth from UnrealEgo2 test split

• Depth from UnrealEgo-RW test split

    bash download_unrealego2_test_sfm.sh
    bash download_unrealego_rw_test_sfm.sh
  

Note that these depth data are different from the synthetic depth maps available on our benchmark challenge page.

Implementation

Dependencies

We tested our code with the following dependencies:

• Python 3.9
• Ubuntu 18.04
• PyTorch 2.0.0
• Cuda 11.7

Please install other dependencies:

pip install -r requirements.txt    

Inference

Trained models

You can download our trained models. Please save them in ./log/(experiment_name).

Inference on UnrealEgo2 test dataset

    bash scripts/test/unrealego2_pose-qa-avg-df_data-ue2_seq5_skip3_B32_lr2-4_pred-seq_local-device_pad.sh

        --data_dir [path to the `UnrealEgoData2_test_rgb` dir]
        --metadata_dir [path to the `UnrealEgoData2_test_sfm` dir]

Please modify the arguments above. The pose predictions will be saved in ./results/UnrealEgoData2_test_pose (raw and zip versions).

Inference on UnrealEgo-RW test dataset

• Model without pre-training on UnrealEgo2

    bash scripts/test/unrealego2_pose-qa-avg-df_data-ue-rw_seq5_skip3_B32_lr2-4_pred-seq_local-device_pad.sh
  
        --data_dir [path to the `UnrealEgoData_rw_test_rgb` dir]
        --metadata_dir [path to the `UnrealEgoData_rw_test_sfm` dir]
  

• Model with pre-training on UnrealEgo2

    bash scripts/test/unrealego2_pose-qa-avg-df_data-ue2_seq5_skip3_B32_lr2-4_pred-seq_local-device_pad_finetuning_epoch5-5.sh
  
        --data_dir [path to the `UnrealEgoData_rw_test_rgb` dir]
        --metadata_dir [path to the `UnrealEgoData_rw_test_sfm` dir]
  

Please modify the arguments above. The pose predictions will be saved in ./results/UnrealEgoData_rw_test_pose (raw and zip versions).

For quantitative results of your methods, please follow the instructions in our benchmark challenge page and submit a zip version.