HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields: Processed data and trained models
收藏资源简介：
############# 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. 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}}
# HOISDF：基于全局有符号距离场（Signed Distance Fields, SDF）约束的三维手-物体位姿估计（CVPR 2024） 作者：Haozhe Qi、Chen Zhao、Mathieu Salzmann、Alexander Mathis 所属机构：洛桑联邦理工学院（EPFL） 发布日期：2024年6月 CVPR官方论文链接：https://openaccess.thecvf.com/content/CVPR2024/papers/Qi_HOISDF_Constraining_3D_Hand-Object_Pose_Estimation_with_Global_Signed_Distance_CVPR_2024_paper.pdf ArXiv预印本链接：https://arxiv.org/abs/2402.17062 -------------------------------- 本数据集为本文《HOISDF：基于全局有符号距离场约束的三维手-物体位姿估计》的配套资源，包含交互物体的预处理数据与SDF采样样本，同时附带训练完成的模型权重文件。 数据集整体目录结构如下： ├── ckpts.zip：包含在DexYCB与HO3Dv2两个数据集上训练得到的模型权重 ├── annotations.zip：包含经预处理的DexYCB与HO3Dv2数据集标注文件，用于优化数据加载效率 ├── simple_ycb_models.zip：包含经预处理的YCB物体模型，支持批量评估任务 ├── test.zip：包含针对DexYCB测试集处理完成的SDF文件 复现本文实验结果的代码可通过以下链接获取：https://github.com/amathislab/HOISDF -------------------------------- 若您认为本项目的代码、模型权重、预测结果或研究思路对您的工作有所帮助，请引用以下文献： @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}}
