{"ID":2852545,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.17137","arxiv_id":"2510.17137","title":"KineDiff3D: Kinematic-Aware Diffusion for Category-Level Articulated Object Shape Reconstruction and Generation","abstract":"Articulated objects, such as laptops and drawers, exhibit significant challenges for 3D reconstruction and pose estimation due to their multi-part geometries and variable joint configurations, which introduce structural diversity across different states. To address these challenges, we propose KineDiff3D: Kinematic-Aware Diffusion for Category-Level Articulated Object Shape Reconstruction and Generation, a unified framework for reconstructing diverse articulated instances and pose estimation from single view input. Specifically, we first encode complete geometry (SDFs), joint angles, and part segmentation into a structured latent space via a novel Kinematic-Aware VAE (KA-VAE). In addition, we employ two conditional diffusion models: one for regressing global pose (SE(3)) and joint parameters, and another for generating the kinematic-aware latent code from partial observations. Finally, we produce an iterative optimization module that bidirectionally refines reconstruction accuracy and kinematic parameters via Chamfer-distance minimization while preserving articulation constraints. Experimental results on synthetic, semi-synthetic, and real-world datasets demonstrate the effectiveness of our approach in accurately reconstructing articulated objects and estimating their kinematic properties.","short_abstract":"Articulated objects, such as laptops and drawers, exhibit significant challenges for 3D reconstruction and pose estimation due to their multi-part geometries and variable joint configurations, which introduce structural diversity across different states. To address these challenges, we propose KineDiff3D: Kinematic-Awa...","url_abs":"https://arxiv.org/abs/2510.17137","url_pdf":"https://arxiv.org/pdf/2510.17137v1","authors":"[\"WenBo Xu\",\"Liu Liu\",\"Li Zhang\",\"Ran Zhang\",\"Hao Wu\",\"Dan Guo\",\"Meng Wang\"]","published":"2025-10-20T04:15:40Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Variational Autoencoder\"]","has_code":false}