Saved in:
Bibliographic Details
Main Authors: Lu, Ruijie, Liu, Yu, Tang, Jiaxiang, Ni, Junfeng, Wang, Yuxiang, Wan, Diwen, Zeng, Gang, Chen, Yixin, Huang, Siyuan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.05763
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909679189229568
author Lu, Ruijie
Liu, Yu
Tang, Jiaxiang
Ni, Junfeng
Wang, Yuxiang
Wan, Diwen
Zeng, Gang
Chen, Yixin
Huang, Siyuan
author_facet Lu, Ruijie
Liu, Yu
Tang, Jiaxiang
Ni, Junfeng
Wang, Yuxiang
Wan, Diwen
Zeng, Gang
Chen, Yixin
Huang, Siyuan
contents Generating articulated objects, such as laptops and microwaves, is a crucial yet challenging task with extensive applications in Embodied AI and AR/VR. Current image-to-3D methods primarily focus on surface geometry and texture, neglecting part decomposition and articulation modeling. Meanwhile, neural reconstruction approaches (e.g., NeRF or Gaussian Splatting) rely on dense multi-view or interaction data, limiting their scalability. In this paper, we introduce DreamArt, a novel framework for generating high-fidelity, interactable articulated assets from single-view images. DreamArt employs a three-stage pipeline: firstly, it reconstructs part-segmented and complete 3D object meshes through a combination of image-to-3D generation, mask-prompted 3D segmentation, and part amodal completion. Second, we fine-tune a video diffusion model to capture part-level articulation priors, leveraging movable part masks as prompt and amodal images to mitigate ambiguities caused by occlusion. Finally, DreamArt optimizes the articulation motion, represented by a dual quaternion, and conducts global texture refinement and repainting to ensure coherent, high-quality textures across all parts. Experimental results demonstrate that DreamArt effectively generates high-quality articulated objects, possessing accurate part shape, high appearance fidelity, and plausible articulation, thereby providing a scalable solution for articulated asset generation. Our project page is available at https://dream-art-0.github.io/DreamArt/.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05763
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DreamArt: Generating Interactable Articulated Objects from a Single Image
Lu, Ruijie
Liu, Yu
Tang, Jiaxiang
Ni, Junfeng
Wang, Yuxiang
Wan, Diwen
Zeng, Gang
Chen, Yixin
Huang, Siyuan
Computer Vision and Pattern Recognition
Generating articulated objects, such as laptops and microwaves, is a crucial yet challenging task with extensive applications in Embodied AI and AR/VR. Current image-to-3D methods primarily focus on surface geometry and texture, neglecting part decomposition and articulation modeling. Meanwhile, neural reconstruction approaches (e.g., NeRF or Gaussian Splatting) rely on dense multi-view or interaction data, limiting their scalability. In this paper, we introduce DreamArt, a novel framework for generating high-fidelity, interactable articulated assets from single-view images. DreamArt employs a three-stage pipeline: firstly, it reconstructs part-segmented and complete 3D object meshes through a combination of image-to-3D generation, mask-prompted 3D segmentation, and part amodal completion. Second, we fine-tune a video diffusion model to capture part-level articulation priors, leveraging movable part masks as prompt and amodal images to mitigate ambiguities caused by occlusion. Finally, DreamArt optimizes the articulation motion, represented by a dual quaternion, and conducts global texture refinement and repainting to ensure coherent, high-quality textures across all parts. Experimental results demonstrate that DreamArt effectively generates high-quality articulated objects, possessing accurate part shape, high appearance fidelity, and plausible articulation, thereby providing a scalable solution for articulated asset generation. Our project page is available at https://dream-art-0.github.io/DreamArt/.
title DreamArt: Generating Interactable Articulated Objects from a Single Image
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.05763