Research

Paper

AI LLM February 23, 2026

DICArt: Advancing Category-level Articulated Object Pose Estimation in Discrete State-Spaces

Authors

Li Zhang, Mingyu Mei, Ailing Wang, Xianhui Meng, Yan Zhong, Xinyuan Song, Liu Liu, Rujing Wang, Zaixing He, Cewu Lu

Abstract

Articulated object pose estimation is a core task in embodied AI. 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 work, we introduce DICArt (DIsCrete Diffusion for Articulation 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 GT 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. Experimental results demonstrate its superior performance and robustness. By integrating discrete generative modeling with structural priors, DICArt offers a new paradigm for reliable category-level 6D pose estimation in complex environments.

Metadata

arXiv ID: 2602.19565
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-02-23
Fetched: 2026-02-24 04:38

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.19565v1</id>\n    <title>DICArt: Advancing Category-level Articulated Object Pose Estimation in Discrete State-Spaces</title>\n    <updated>2026-02-23T07:30:47Z</updated>\n    <link href='https://arxiv.org/abs/2602.19565v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.19565v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Articulated object pose estimation is a core task in embodied AI. 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 work, we introduce DICArt (DIsCrete Diffusion for Articulation 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 GT 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. Experimental results demonstrate its superior performance and robustness. By integrating discrete generative modeling with structural priors, DICArt offers a new paradigm for reliable category-level 6D pose estimation in complex environments.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-23T07:30:47Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Li Zhang</name>\n    </author>\n    <author>\n      <name>Mingyu Mei</name>\n    </author>\n    <author>\n      <name>Ailing Wang</name>\n    </author>\n    <author>\n      <name>Xianhui Meng</name>\n    </author>\n    <author>\n      <name>Yan Zhong</name>\n    </author>\n    <author>\n      <name>Xinyuan Song</name>\n    </author>\n    <author>\n      <name>Liu Liu</name>\n    </author>\n    <author>\n      <name>Rujing Wang</name>\n    </author>\n    <author>\n      <name>Zaixing He</name>\n    </author>\n    <author>\n      <name>Cewu Lu</name>\n    </author>\n  </entry>"
}