Generating human-object interactions (HOIs) with multiple objects is challenging because the resulting motions arise from different underlying causes. Human motion reflects semantic intent, intentionally manipulated objects must remain coordinated with the human, while surrounding objects move primarily as physical consequences of contact and collision. We present BUMP, a text-driven framework for multi-object HOI generation based on a simple principle: learn intentional motion and simulate physical consequences. Our method first generates full-body human motion from text and scene context, then predicts trajectories for a small number of intentionally manipulated driver objects conditioned on the human motion. We then obtain responder object motions through physics simulation, allowing the framework to handle varying numbers and configurations of surrounding objects without expanding the learned trajectory output space. To address the scarcity of paired full-body multi-object HOI data, we combine heterogeneous supervision from human-only motion, full-body HOI, and hand-centric manipulation data augmented with plausible body motion. We further introduce outcome-conditioned interaction editing, which infers a local modification of the causal driver object trajectory from a desired responder object behavior without requiring an explicit target driver object trajectory. Experiments demonstrate strong performance on both single-object and multi-object HOI benchmarks. Qualitative results showcase diverse scenarios involving inter-object relationships and edits, highlighting the advantage of our unified model formulation.
Figures & tables
Figure 1: Overview of BUMP. Given a text prompt and an initial scene, BUMP generates intentional human and driver object motion while obtaining physically induced responder object motion through simulation.
Figure 2: Overview of the generation and editing pipeline. We generate human motion, predict hand-driver object contacts, and generate driver object trajectories conditioned on both. Physics simulation produces responder object motions. For outcome-conditioned editing, we locally modify the driver object trajectory, validate the resulting responder object motion through simulation, and align the human motion with the edited driver object while preserving the original motion.
Figure 3: Outcome-conditioned interaction editing. We compare the original and edited interactions under different responder object-level goals. The edits produce the requested changes in the physical outcomes while preserving the overall interaction.
Figure 4: Qualitative comparison across different numbers of interacting objects. We compare representative generations on InterAct and HIMO using temporal snapshots and hand-object close-ups.