paper-with-me

홈 › Papers

RecDiffusion: Rectangling for Image Stitching with Diffusion Models

2024-03-28 · CVPR 2024 1 · Tianhao Zhou, Haipeng Li, Ziyi Wang, Ao Luo, Chen-Lin Zhang, Jiajun Li, Bing Zeng, Shuaicheng Liu

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.

📄 PDF Abstract BibTeX arXiv:2403.19164

Code (1)

lhaippp/recdiffusion 공식 구현 pytorch

Tasks

Image Stitching

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model

2024-04-23 · Ziqi Xie, Weidong Zhao, Xianhui Liu, Jian Zhao 외

Deep learning-based image stitching pipelines are typically divided into three cascading stages: registration, fusion, and rectangling. Each stage requires its own network training and is tightly coupled to the others, l…

Image Stitching

Deep Rectangling for Image Stitching: A Learning Baseline

2022-03-08 · CVPR 2022 1 · Lang Nie, Chunyu Lin, Kang Liao, Shuaicheng Liu 외

Stitched images provide a wide field-of-view (FoV) but suffer from unpleasant irregular boundaries. To deal with this problem, existing image rectangling methods devote to searching an initial mesh and optimizing a targe…

DiversityImage Stitching

Content-Preserving Image Stitching with Piecewise Rectangular Boundary Constraints

2021-07-01 · IEEE Transactions on Visualization and Computer Graphics 2021 7 · Yun Zhang, Yu-Kun Lai, and Fang-Lue Zhang, Member 외

Abstract—This paper proposes an approach to content- preserving image stitching with regular boundary constraints, which aims to stitch multiple images to generate a panoramic image with a piecewise rectangular bounda…

Image Stitching

Modification Takes Courage: Seamless Image Stitching via Reference-Driven Inpainting

2024-11-15 · Ziqi Xie, Xiao Lai, Weidong Zhao, Xianhui Liu 외

Current image stitching methods often produce noticeable seams in challenging scenarios such as uneven hue and large parallax. To tackle this problem, we propose the Reference-Driven Inpainting Stitcher (RDIStitcher), wh…

Image Stitching

RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning

2023-01-04 · ICCV 2023 1 · Kang Liao, Lang Nie, Chunyu Lin, Zishuo Zheng 외

The wide-angle lens shows appealing applications in VR technologies, but it introduces severe radial distortion into its captured image. To recover the realistic scene, previous works devote to rectifying the content of …