SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis

TL;DR

SyncMV4D introduces a novel multi-view joint diffusion framework that generates synchronized 3D-aware hand-object interaction videos and motions, overcoming limitations of single-view and high-quality data dependence.

Contribution

It is the first model to jointly generate synchronized multi-view HOI videos and 4D motions by unifying visual, motion, and multi-view geometry priors.

Findings

Outperforms state-of-the-art in realism and consistency

Generates plausible 4D motions from multi-view videos

Achieves high multi-view coherence in generated videos

Abstract

Hand-Object Interaction (HOI) generation plays a critical role in advancing applications across animation and robotics. Current video-based methods are predominantly single-view, which impedes comprehensive 3D geometry perception and often results in geometric distortions or unrealistic motion patterns. While 3D HOI approaches can generate dynamically plausible motions, their dependence on high-quality 3D data captured in controlled laboratory settings severely limits their generalization to real-world scenarios. To overcome these limitations, we introduce SyncMV4D, the first model that jointly generates synchronized multi-view HOI videos and 4D motions by unifying visual prior, motion dynamics, and multi-view geometry. Our framework features two core innovations: (1) a Multi-view Joint Diffusion (MJD) model that co-generates HOI videos and intermediate motions, and (2) a Diffusion Points Aligner (DPA) that refines the coarse intermediate motion into globally aligned 4D metric point tracks. To tightly couple 2D appearance with 4D dynamics, we establish a closed-loop, mutually enhancing cycle. During the diffusion denoising process, the generated video conditions the refinement of the 4D motion, while the aligned 4D point tracks are reprojected to guide next-step joint generation. Experimentally, our method demonstrates superior performance to state-of-the-art alternatives in visual realism, motion plausibility, and multi-view consistency.