Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| 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 |