RecDiffusion: Rectangling for Image Stitching with Diffusion Models
arxiv(2024)
摘要
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, 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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要