ProciGen-video dataset for "InterTrack: Tracking Human Object Interaction without Object Templates" (3DV'25)

DOI

A large scale synthetic dataset about dynamic human-object interactions. It features about 10 hours of video with 8337 sequences and 2M images. The generation of this dataset is described in the paper "InterTrack: Tracking Human Object Interaction without Object Templates" (3DV'25). Please check the github repo for detailed file structure of the dataset: https://github.com/xiexh20/ProciGen If you use our data, please cite: @inproceedings{xie2024InterTrack, title = {InterTrack: Tracking Human Object Interaction without Object Templates}, author = {Xie, Xianghui and Lenssen, Jan Eric and Pons-Moll, Gerard}, booktitle = {International Conference on 3D Vision (3DV)}, month = {March}, year = {2025}, }

Identifier
DOI https://doi.org/10.17617/3.B6BM5R
Metadata Access https://edmond.mpg.de/api/datasets/export?exporter=dataverse_json&persistentId=doi:10.17617/3.B6BM5R
Provenance
Creator Xie, Xianghui
Publisher Edmond
Publication Year 2025
OpenAccess true
Contact xxie(at)mpi-inf.mpg.de
Representation
Language English
Resource Type Dataset
Version 3
Discipline Other