RecDiffusion: Rectangling for Image Stitching with Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911818339844096 |
|---|---|
| author | Zhou, Tianhao Li, Haipeng Wang, Ziyi Luo, Ao Zhang, Chen-Lin Li, Jiajun Zeng, Bing Liu, Shuaicheng |
| author_facet | Zhou, Tianhao Li, Haipeng Wang, Ziyi Luo, Ao Zhang, Chen-Lin Li, Jiajun Zeng, Bing Liu, Shuaicheng |
| contents | Image stitching from different captures often results in non-rectangular boundaries, which is often considered unappealing. To solve non-rectangular boundaries, current solutions involve cropping, which discards image content, inpainting, which can introduce unrelated content, or warping, which can distort non-linear features and introduce artifacts. To overcome these issues, we introduce a novel diffusion-based learning framework, \textbf{RecDiffusion}, for image stitching rectangling. This framework combines Motion Diffusion Models (MDM) to generate motion fields, effectively transitioning from the stitched image's irregular borders to a geometrically corrected intermediary. Followed by Content Diffusion Models (CDM) for image detail refinement. Notably, our sampling process utilizes a weighted map to identify regions needing correction during each iteration of CDM. Our RecDiffusion ensures geometric accuracy and overall visual appeal, surpassing all previous methods in both quantitative and qualitative measures when evaluated on public benchmarks. Code is released at https://github.com/lhaippp/RecDiffusion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19164 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RecDiffusion: Rectangling for Image Stitching with Diffusion Models Zhou, Tianhao Li, Haipeng Wang, Ziyi Luo, Ao Zhang, Chen-Lin Li, Jiajun Zeng, Bing Liu, Shuaicheng Computer Vision and Pattern Recognition Image stitching from different captures often results in non-rectangular boundaries, which is often considered unappealing. To solve non-rectangular boundaries, current solutions involve cropping, which discards image content, inpainting, which can introduce unrelated content, or warping, which can distort non-linear features and introduce artifacts. To overcome these issues, we introduce a novel diffusion-based learning framework, \textbf{RecDiffusion}, for image stitching rectangling. This framework combines Motion Diffusion Models (MDM) to generate motion fields, effectively transitioning from the stitched image's irregular borders to a geometrically corrected intermediary. Followed by Content Diffusion Models (CDM) for image detail refinement. Notably, our sampling process utilizes a weighted map to identify regions needing correction during each iteration of CDM. Our RecDiffusion ensures geometric accuracy and overall visual appeal, surpassing all previous methods in both quantitative and qualitative measures when evaluated on public benchmarks. Code is released at https://github.com/lhaippp/RecDiffusion. |
| title | RecDiffusion: Rectangling for Image Stitching with Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.19164 |