Uni-Inter: Unifying 3D Human Motion Synthesis Across Diverse Interaction Contexts

TL;DR

Uni-Inter introduces a unified, task-agnostic framework for 3D human motion synthesis across diverse interaction scenarios using a novel volumetric representation, enabling better generalization and coherent behavior modeling.

Contribution

The paper proposes Uni-Inter, a novel unified framework with the UIV representation that generalizes across multiple interaction types in human motion synthesis.

Findings

Achieves competitive performance across interaction tasks.

Generalizes well to unseen entity combinations.

Models fine-grained spatial dependencies effectively.

Abstract

We present Uni-Inter, a unified framework for human motion generation that supports a wide range of interaction scenarios: including human-human, human-object, and human-scene-within a single, task-agnostic architecture. In contrast to existing methods that rely on task-specific designs and exhibit limited generalization, Uni-Inter introduces the Unified Interactive Volume (UIV), a volumetric representation that encodes heterogeneous interactive entities into a shared spatial field. This enables consistent relational reasoning and compound interaction modeling. Motion generation is formulated as joint-wise probabilistic prediction over the UIV, allowing the model to capture fine-grained spatial dependencies and produce coherent, context-aware behaviors. Experiments across three representative interaction tasks demonstrate that Uni-Inter achieves competitive performance and generalizes well to novel combinations of entities. These results suggest that unified modeling of compound interactions offers a promising direction for scalable motion synthesis in complex environments.