StructBiHOI: 结构化关节建模用于长时程双臂手-物体交互生成
DuetHOI: Language-Guided Bimanual Hand--Object Motion Generation with Articulation Planning and Contact Refinement
AI总结：
StructBiHOI通过结构化关节建模框架实现长时程双臂手-物体交互生成，提升稳定性和效率。
摘要：
近期3D手-物体交互（HOI）生成的研究主要集中在单手抓取合成，而双臂操作仍显著更具挑战性。长时程规划不稳定、细粒度关节运动和复杂的跨手协调使连贯的双臂生成困难，特别是在多模态条件下。现有方法往往难以同时确保时间一致性、物理合理性以及语义对齐性。我们提出了StructBiHOI，一种用于长时程双臂HOI生成的结构化关节建模框架。我们的关键见解是将时间关节规划与帧级操作细化结构化分离。具体而言，一个jointVAE在物体几何和任务语义条件下建模长期关节演变，而一个maniVAE在单帧级别上细化精细的手部姿态。为了实现稳定且高效的长序列生成，我们结合了基于Mamba的状态空间启发式扩散去噪器，该去噪器以线性复杂度建模长距离依赖。这种分层设计促进了连贯的双臂协调和关节物体交互。在双臂操作和单手抓取基准测试中进行了广泛的实验，结果表明，我们的方法在长时程稳定性、运动真实性和计算效率方面均优于强基线方法。
英文摘要：
Bimanual articulated-object interaction generation requires a model to capture the evolution of object articulation, coordination between the two hands, and fine-grained hand--object contact. Existing methods typically encode object and hand motion as a unified high-dimensional sequence, making it difficult to explicitly accommodate the different scales of manipulation progress, relative bimanual motion, and local hand pose. We propose \textbf{DuetHOI}, a structured framework for bimanual articulated-object interaction generation. DuetHOI first uses ContactVAE to predict contact intent on the object surface from language and object geometry. Conditioned on this spatial intent, ArtPlanner provides a trajectory-level articulation reference, and DualFormer generates the global interaction using object states, object-centered hand positions, and compact hand-pose tokens learned by ManiVAE. After global generation, ProxiRefine fixes the object trajectory and residually corrects the two hands using current hand--object proximity, improving local surface alignment. Experiments across articulated and rigid objects and single- and bimanual settings show that DuetHOI outperforms three adapted baselines on most contact and hand--object consistency metrics, with particularly strong results in bimanual articulated interaction generation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
