# HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction Source: [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction]() Collection index: [llms.txt]() Data updated: 2026-01-02T04:47:36.692Z Authors: Yunze Liu, Yun Liu, Che Jiang, Kangbo Lyu, Weikang Wan, Hao Shen, Boqiang Liang, Zhoujie Fu, He Wang, Li Yi Published: 2022-03-03T09:02:52.000Z ## Abstract We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction. HOI4D consists of 2.4M RGB-D egocentric video frames over 4000 sequences collected by 4 participants interacting with 800 different object instances from 16 categories over 610 different indoor rooms. Frame-wise annotations for panoptic segmentation, motion segmentation, 3D hand pose, category-level object pose and hand action have also been provided, together with reconstructed object meshes and scene point clouds. With HOI4D, we establish three benchmarking tasks to promote category-level HOI from 4D visual signals including semantic segmentation of 4D dynamic point cloud sequences, category-level object pose tracking, and egocentric action segmentation with diverse interaction targets. In-depth analysis shows HOI4D poses great challenges to existing methods and produces great research opportunities. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Dexterous Manipulation on HOI4D](): Dexterous Manipulation; HOI4D; Object Rotation Error (Er): 10.4. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()