five

MMHOI Dataset: Modeling Complex 3D Multi-Human Multi-Object Interactions

收藏
Zenodo2025-12-01 更新2026-05-26 收录
下载链接:
https://zenodo.org/doi/10.5281/zenodo.17711785
下载链接
链接失效反馈
官方服务:
资源简介:
Introduction The MMHOI dataset addresses the challenge of modeling real-world scenes with multiple humans and objects interacting in causal, goal-oriented, or cooperative ways. Existing 3D human-object interaction (HOI) benchmarks capture only a subset of these complex interactions. MMHOI closes this gap by providing a large-scale dataset with comprehensive 3D shape and pose annotations for every person and object, covering 78 action categories and 14 interaction-specific body parts across 12 everyday scenarios. MMHOI is designed to foster research in multi-human multi-object interactions and serves as a benchmark for next-generation HOI algorithms. All necessary data for training, validation, and testing are publicly released. At a Glance Unzipped Size: 173 GB The unzipped folder contains a README.md that describes the contents of each subfolder. Contents: 20240418_personM_personC_from4C_all_30skip_start-end: 13G 20240417_personM_personC_to3C_finish: 1.7G 20240418_personB_personC_noC1andC2_all_30_skip_start-end: 3.1G 20240412_personA_personC: 19G 20240508_personJ_personK_30_skip_start-end: 16G 20240423_personB_personC_and_C2_all__start-end: 3.3G 20240417_personM_personB_finish: 4.6G 20240508_personE_personD_all_30skip_start-end: 17G Single20240531_personA_all_30skip_start-end: 4.2G 20240412_personA_personB: 24G 20240426_personL_personC_all_30skip_start-end: 17G 20240424_personB_personD_all_start-end: 13G 20240510_personH_personI: 16G 20240426_personB_personG_all_30skip_start-end: 7.0G 20240423_personM_personC_30_skip_all_start-end: 17G Other Resources The code associated with the approach will be released separately on GitHub. Citation If you use the MMHOI dataset in your research, please cite our contribution: @inproceedings{cherian2021insegan, title={MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions}, author={K. Kogashi, A. Cherian, and M-Y. J. Kuo}, booktitle={Proceedings of the Winter Conference on Applications of Computer Vision}, year={2026} } License The MMHOI dataset is released under CC-BY-SA-4.0 license. All data: Created by Mitsubishi Electric Research Laboratories (MERL), 2025-2026 SPDX-License-Identifier: CC-BY-SA-4.0
提供机构:
Zenodo
创建时间:
2025-12-01
二维码
社区交流群
二维码
科研交流群
商业服务