SituHOI：可扩展采集场景化全身人物交互数据集

View PDF HTML (experimental)

Abstract:Modeling human-object interaction (HOI) in real environments requires jointly representing whole-body motion, manipulated objects, and scene geometry, yet existing datasets trade off scalable capture against structured, scene-aligned supervision. We introduce SituHOI, a large-scale RGB-D dataset containing 18,429 annotated clips across 16 indoor rooms and approximately 86 hours of quality-screened activity. It pairs recordings from a single moving RGB-D camera with static scene scans, object geometry, language descriptions, and estimated human and object trajectories. Using the scans as persistent references, our pipeline combines camera localization and depth-based metric alignment with human mesh recovery, object tracking, and temporal refinement to register all geometric annotations in a shared floor-aligned frame. These data support FlexHOI-Bench, a goal-conditioned joint motion prediction benchmark with variable observation and prediction durations. Given observed histories, scene and object geometry, and a terminal object pose, models predict future human and object motion. We provide SharedHOI as a reference predictor and evaluate world-space accuracy and human-object coordination. On a MoCap subset, our pipeline reduces human G-MPJPE from 195.4 to 68.3 mm and object translation error from 43.0 to 28.7 mm. SharedHOI leads four adapted baselines on all three aggregate FlexHOI-Bench metrics. Data will be released upon acceptance. An anonymized code repository is available at this https URL.

Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.23980 [cs.CV]
	(or arXiv:2610.23980v2 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2610.23980 arXiv-issued DOI via DataCite

Submission history

From: Qifan Wang [view email]
[v1] Tue, 13 Oct 2026 17:39:10 UTC (5,549 KB)
[v2] Thu, 29 Oct 2026 11:03:41 UTC (5,549 KB)