ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration

TL;DR

ONE-SHOT introduces a novel, efficient framework for compositional human-environment video synthesis that disentangles signals and maintains consistency over long sequences, outperforming existing methods.

Contribution

The paper proposes a parameter-efficient, disentangled generative process with novel spatial correspondence and hybrid context mechanisms for improved video synthesis.

Findings

Outperforms state-of-the-art methods in structural control and diversity.

Supports long-horizon, minute-level video synthesis.

Introduces a canonical-space injection and Dynamic-Grounded-RoPE for spatial decoupling.

Abstract

Recent advances in Video Foundation Models (VFMs) have revolutionized human-centric video synthesis, yet fine-grained and independent editing of subjects and scenes remains a critical challenge. Recent attempts to incorporate richer environment control through rigid 3D geometric compositions often encounter a stark trade-off between precise control and generative flexibility. Furthermore, the heavy 3D pre-processing still limits practical scalability. In this paper, we propose ONE-SHOT, a parameter-efficient framework for compositional human-environment video generation. Our key insight is to factorize the generative process into disentangled signals. Specifically, we introduce a canonical-space injection mechanism that decouples human dynamics from environmental cues via cross-attention. We also propose Dynamic-Grounded-RoPE, a novel positional embedding strategy that establishes spatial correspondences between disparate spatial domains without any heuristic 3D alignments. To support long-horizon synthesis, we introduce a Hybrid Context Integration mechanism to maintain subject and scene consistency across minute-level generations. Experiments demonstrate that our method significantly outperforms state-of-the-art methods, offering superior structural control and creative diversity for video synthesis. Our project has been available on: https://martayang.github.io/ONE-SHOT/.