Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.13863 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913035191320576 |
|---|---|
| author | Tong, Zebei Chen, Hongchang Lei, Yujie Chen, Gang Liu, Yushi Zheng, Zhi Chen, Hao Zhang, Jieming Li, Ying Cao, Dongpu |
| author_facet | Tong, Zebei Chen, Hongchang Lei, Yujie Chen, Gang Liu, Yushi Zheng, Zhi Chen, Hao Zhang, Jieming Li, Ying Cao, Dongpu |
| contents | Image generation technology can synthesize condition-specific images to supplement real-world industrial anomaly data and enhance anomaly detection model performance. Existing generation techniques rarely account for the pose and orientation of industrial components in assembly, making the generated images difficult to utilize for downstream application. To solve this, we propose a novel image synthesis approach, called PostureObjectStitch, that achieves accurate generation to meet the requirement of industrial assembly. A condition decoupling approach is introduced to separate input multi-view images into high-frequency, texture, and RGB features. The feature temporal modulation mechanism adapts these features across diffusion model time-steps, enabling progressive generation from coarse to fine details while maintaining consistency. To ensure semantic accuracy, we introduce a conditional loss that enhances critical industrial elements and a geometric prior that guides component positioning for correct assembly relationships. Comprehensive experimental results on the MureCom dataset, our newly contributed DreamAssembly dataset, and the downstream application validate the outstanding performance of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13863 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios Tong, Zebei Chen, Hongchang Lei, Yujie Chen, Gang Liu, Yushi Zheng, Zhi Chen, Hao Zhang, Jieming Li, Ying Cao, Dongpu Computer Vision and Pattern Recognition Image generation technology can synthesize condition-specific images to supplement real-world industrial anomaly data and enhance anomaly detection model performance. Existing generation techniques rarely account for the pose and orientation of industrial components in assembly, making the generated images difficult to utilize for downstream application. To solve this, we propose a novel image synthesis approach, called PostureObjectStitch, that achieves accurate generation to meet the requirement of industrial assembly. A condition decoupling approach is introduced to separate input multi-view images into high-frequency, texture, and RGB features. The feature temporal modulation mechanism adapts these features across diffusion model time-steps, enabling progressive generation from coarse to fine details while maintaining consistency. To ensure semantic accuracy, we introduce a conditional loss that enhances critical industrial elements and a geometric prior that guides component positioning for correct assembly relationships. Comprehensive experimental results on the MureCom dataset, our newly contributed DreamAssembly dataset, and the downstream application validate the outstanding performance of our method. |
| title | PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.13863 |