FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions
Overview
This paper proposes FlowHOI, a two-stage flow-matching framework that generates temporally coherent hand-object interaction sequences for dexterous robot manipulation. It conditions on egocentric observations, language instructions, and 3D Gaussian splatting scene reconstructions, achieving higher action recognition accuracy and physics simulation success rates than diffusion-based baselines, with real-robot execution demonstrated on four tasks.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · physics simulation success rate: 1.7 other · Basis not reported
“prior for robust generation. Across the GRAB and HOT3D benchmarks, FlowHOI achieves the highest action recognition accuracy and a 1.7$\times$ higher physics simulation success rate than the strongest diffusion-based baseline, while delivering a 40$\times$ inference speedup. We further demonstrate real-robot execution on four dexterous manipulation tasks, illustrating the feasibility of retargeting generated HOI repr”
Exact source · revision 1Source owner not reported
Reported quantity · inference speedup: 40 other · Basis not reported
“prior for robust generation. Across the GRAB and HOT3D benchmarks, FlowHOI achieves the highest action recognition accuracy and a 1.7$\times$ higher physics simulation success rate than the strongest diffusion-based baseline, while delivering a 40$\times$ inference speedup. We further demonstrate real-robot execution on four dexterous manipulation tasks, illustrating the feasibility of retargeting generated HOI repr”
Exact source · revision 1Source owner not reported
Evidence dependency changes (2)
- 2026-10-30T19:47:44.260Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T19:47:33.150Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalFlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation
This paper proposes FlowHOI, a two-stage flow-matching framework that generates temporally coherent hand-object interaction sequences for dexterous robot manipulation. It conditions on egocentric observations, language instructions, and 3D Gaussian splatting scene reconstructions, achieving higher action recognition accuracy and physics simulation success rates than diffusion-based baselines, with real-robot execution demonstrated on four tasks.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).