这是indexloc提供的服务,不要输入任何密码
Published June 19, 2024 | Version v3
Dataset Open

Processed data and trained models for "HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields"

  • 1. ROR icon École Polytechnique Fédérale de Lausanne

Description

#############

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields, CVPR 2024

#############

Haozhe Qi, Chen Zhao, Mathieu Salzmann, Alexander Mathis.

Affiliation: EPFL

Date: June, 2024

Link to the CVPR article: https://openaccess.thecvf.com/content/CVPR2024/papers/Qi_HOISDF_Constraining_3D_Hand-Object_Pose_Estimation_with_Global_Signed_Distance_CVPR_2024_paper.pdf

Link to the Arxiv article: https://arxiv.org/abs/2402.17062

--------------------------------

Here we provide the data of our article "HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields". It contains the preprocessed data of the interacting objects and SDF samples. Meanwhile, we also include the trained model weights here.

The overall structure of the data is:

├── ckpts.zip                                - Contains the trained weights model on different datasets (DexYCB and HO3Dv2)
├── annotations.zip                     - Contains the preprocessed annotations of DexYCB and HO3Dv2 for efficient data loading.
├── simple_ycb_models.zip         - Contains the preprocessed YCB objects for batched evaluation.
├── test.zip                                  - Contains the processed SDF files for DexYCB test set.
├── ho3d_release.zip                   - Contains the HO3Dv2 submission trained with HO3D training set.
├── ho3d_render_release.zip       - Contains the HO3Dv2 submission trained with HO3D training set and rendering set.
 

The code to reproduce the results is available at: https://github.com/amathislab/HOISDF
 
--------------------------------

If you find our code, weights, predictions or ideas useful, please cite:

@inproceedings{qi2024hoisdf,
  title={HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields},
  author={Qi, Haozhe and Zhao, Chen and Salzmann, Mathieu and Mathis, Alexander},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={10392--10402},
  year={2024}
}

Files

annotations.zip

Files (23.9 GB)

Name Size Download all
md5:33d820de400203505b8d19a7758e186d
1.2 GB Preview Download
md5:d2cfc1907befbf6e4ad5489328652b97
3.0 GB Preview Download
md5:9baf8f910502e36001964ee8c8d73e17
241.4 MB Preview Download
md5:4c0538f7b473e053090e3f8599c6afd6
241.4 MB Preview Download
md5:a29083a3f0bc0938736bf090e6b8d0b1
1.9 kB Preview Download
md5:3e63d67e5ada8661f77b1e066a10ecda
1.6 MB Preview Download
md5:23b7454f2bc940229f85b7042045f4fd
19.3 GB Preview Download

Additional details

Related works

Documents
Publication: arXiv:2402.17062 (arXiv)
Publication: https://openaccess.thecvf.com/content/CVPR2024/papers/Qi_HOISDF_Constraining_3D_Hand-Object_Pose_Estimation_with_Global_Signed_Distance_CVPR_2024_paper.pdf (Other)
Publication: 10.1109/CVPR52733.2024.00989 (DOI)

Dates

Accepted
2024
CVPR2024