Search papers, labs, and topics across Lattice.
The paper introduces DynaHOI-Gym, a new online closed-loop platform for benchmarking hand motion generation in dynamic hand-object interaction (HOI) scenarios, addressing the limitations of existing benchmarks focused on static objects. To facilitate research, the authors release DynaHOI-10M, a large-scale dataset comprising 10 million frames and 180K hand capture trajectories with diverse target motions. They also present an observe-before-act (ObAct) baseline that leverages spatiotemporal attention, demonstrating improved location success rates in the dynamic HOI setting.
Current hand-object interaction benchmarks fail to capture the complexity of dynamic environments, but DynaHOI offers a new platform and large-scale dataset to fill this gap.
Most existing hand motion generation benchmarks for hand-object interaction (HOI) focus on static objects, leaving dynamic scenarios with moving targets and time-critical coordination largely untested. To address this gap, we introduce the DynaHOI-Gym, a unified online closed-loop platform with parameterized motion generators and rollout-based metrics for dynamic capture evaluation. Built on DynaHOI-Gym, we release DynaHOI-10M, a large-scale benchmark with 10M frames and 180K hand capture trajectories, whose target motions are organized into 8 major categories and 22 fine-grained subcategories. We also provide a simple observe-before-act baseline (ObAct) that integrates short-term observations with the current frame via spatiotemporal attention to predict actions, achieving an 8.1% improvement in location success rate.
