DICArt：在离散状态空间中推进类别级铰接物体姿态估计
DICArt: Advancing Category-level Articulated Object Pose Estimation in Discrete State-Spaces
将类别级铰接物体姿态估计建模为离散扩散过程，利用分层运动学耦合和流决策器在离散状态空间中逐步去噪，为复杂铰接物体的 6D 姿态估计提供了新思路。
原文依据 DICArt progressively denoises a noisy pose representation through a learned reverse diffusion procedure to recover the ground-truth pose.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论铰接物体姿态估计是具身智能和计算机视觉中的核心任务。现有方法通常在连续空间中回归姿态，但往往难以应对 1) 在庞大复杂的搜索空间中导航，以及 2) 无法融入内在的运动学约束。本文提出 DICArt（用于铰接物体姿态估计的离散扩散），一种新颖的框架，将姿态估计建模为条件离散扩散过程。DICArt 不在连续域中操作，而是通过学习的逆扩散过程逐步对含噪姿态表示去噪，以恢复真实姿态。为提高建模保真度，我们提出一种灵活的流决策器，动态决定每个词元应被去噪还是重置，从而在扩散过程中有效平衡真实分布与噪声分布。此外，我们引入分层运动学耦合策略，分层估计每个刚性部件的姿态，以尊重物体的运动学结构。我们在合成数据集和真实世界数据集上对 DICArt 进行了验证，这些数据集包含多铰链铰接物体。实验结果表明，其性能与鲁棒性优于最优基线。通过将离散生成建模与结构先验相结合，DICArt 为复杂环境中可靠的类别级 6D 姿态估计提供了新范式。代码将在接收后公开。
英文原文摘要 1461 字符
Articulated object pose estimation is a core task in embodied AI and computer vision. Existing methods typically regress poses in a continuous space, but often struggle with 1) navigating a large, complex search space and 2) failing to incorporate intrinsic kinematic constraints. In this paper, we introduce DICArt (DIsCrete Diffusion for Articulated Object Pose Estimation), a novel framework that formulates pose estimation as a conditional discrete diffusion process. Instead of operating in a continuous domain, DICArt progressively denoises a noisy pose representation through a learned reverse diffusion procedure to recover the ground-truth pose.To improve modeling fidelity, we propose a flexible flow decider that dynamically determines whether each token should be denoised or reset, effectively balancing the real and noise distributions during diffusion. Additionally, we incorporate a hierarchical kinematic coupling strategy, estimating the pose of each rigid part hierarchically to respect the object's kinematic structure.We validate DICArt on both synthetic and real-world datasets with multi-hinged articulated objects. Experimental results demonstrate its superior performance and robustness over state-of-the-art baselines. By integrating discrete generative modeling with structural priors, DICArt offers a new paradigm for reliable category-level 6D pose estimation in complex environments. Codewill be publicly available upon acceptance.