StructBiHOI: Structured Articulation Modeling for Long--Horizon Bimanual Hand--Object Interaction Generation

TL;DR

StructBiHOI introduces a hierarchical framework for long-horizon bimanual hand-object interaction generation, disentangling joint planning from frame-level refinement to improve stability, realism, and efficiency.

Contribution

It presents a novel structured articulation modeling approach combining jointVAE and maniVAE with a diffusion denoiser for stable, long-term bimanual interaction synthesis.

Findings

Achieves superior long-horizon stability and motion realism.

Demonstrates improved computational efficiency over baselines.

Excels in complex dual-hand coordination tasks.

Abstract

Recent progress in 3D hand--object interaction (HOI) generation has primarily focused on single--hand grasp synthesis, while bimanual manipulation remains significantly more challenging. Long--horizon planning instability, fine--grained joint articulation, and complex cross--hand coordination make coherent bimanual generation difficult, especially under multimodal conditions. Existing approaches often struggle to simultaneously ensure temporal consistency, physical plausibility, and semantic alignment over extended sequences. We propose StructBiHOI, a Structured articulation modeling framework for long-horizon Bimanual HOI generation. Our key insight is to structurally disentangle temporal joint planning from frame--level manipulation refinement. Specifically, a jointVAE models long-term joint evolution conditioned on object geometry and task semantics, while a maniVAE refines fine-grained hand poses at the single--frame level. To enable stable and efficient long--sequence generation, we incorporate a state--space--inspired diffusion denoiser based on Mamba, which models long--range dependencies with linear complexity. This hierarchical design facilitates coherent dual-hand coordination and articulated object interaction. Extensive experiments on bimanual manipulation and single-hand grasping benchmarks demonstrate that our method achieves superior long--horizon stability, motion realism, and computational efficiency compared to strong baselines.