HOIGS通过显式建模人物交互变形，提升动态场景重建精度。
HOIGS: Human-Object Interaction Gaussian Splatting
- 引入交叉注意力模块，显式建模人与物体间的交互变形。
- 在多个数据集上优于当前最优的4D高斯方法，尤其在遮挡和接触场景中表现突出。
- 适合需要高保真动态人体-物体交互重建的研究者使用。
重建包含复杂人-物交互的动态场景是计算机视觉与图形学中的基础挑战。现有高斯点阵方法或依赖人体姿态先验而忽略动态物体，或在单一场中近似所有运动，难以捕捉丰富的交互动态。为此，我们提出人-物交互高斯点阵（HOIGS），通过基于交叉注意力的交互模块显式建模人与物体间由交互引发的形变。分别采用HexPlane表示人体特征，用三次埃尔米特样条（CHS）表示物体特征，融合异构特征以有效捕捉相互依赖的运动，在存在遮挡、接触及物体操作的场景中显著提升形变估计精度。在多个数据集上的综合实验表明，本方法持续优于当前最优的人体中心与4D高斯方法，凸显了显式建模人-物交互对高保真重建的重要性。
原文摘要 · Abstract (English)
Reconstructing dynamic scenes with complex human-object interactions is a fundamental challenge in computer vision and graphics. Existing Gaussian Splatting methods either rely on human pose priors while neglecting dynamic objects, or approximate all motions within a single field, limiting their ability to capture interaction-rich dynamics. To address this gap, we propose Human-Object Interaction Gaussian Splatting (HOIGS), which explicitly models interaction-induced deformation between humans and objects through a cross-attention-based HOI module. Distinct deformation baselines are employed to extract features: HexPlane for humans and Cubic Hermite Spline (CHS) for objects. By integrating these heterogeneous features, HOIGS effectively captures interdependent motions and improves deformation estimation in scenarios involving occlusion, contact, and object manipulation. Comprehensive experiments on multiple datasets demonstrate that our method consistently outperforms state-of-the-art human-centric and 4D Gaussian approaches, highlighting the importance of explicitly modeling human-object interactions for high-fidelity reconstruction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。