【图像拼接/扩散模型】论文精读：RecDiffusion: Rectangling for Image Stitching with Diffusion Models（重磅！CVPR 2024）

最新推荐文章于 2024-12-12 12:53:11 发布

十小大

最新推荐文章于 2024-12-12 12:53:11 发布

阅读量7.5k

点赞数 27

分类专栏：图像拼接论文精读文章标签：计算机视觉人工智能深度学习图像拼接扩散模型论文阅读论文笔记

本文链接：https://blog.csdn.net/qq_36584673/article/details/137167156

版权

图像拼接论文精读专栏收录该内容

140 篇文章 ¥179.90 ¥299.90

订阅专栏

RecDiffusion是CVPR 2024提出的一种新方法，它使用扩散模型来解决图像拼接后的非矩形边界问题。传统方法如裁剪或修复可能会丢失或引入不相关的内容，而RecDiffusion结合运动扩散模型(MDM)和内容扩散模型(CDM)，通过学习的去噪过程生成几何准确且视觉上令人愉悦的矩形图像。MDM生成运动场，CDM细化图像细节，通过加权图采样策略减少噪声和伪影。实验表明RecDiffusion在定量和定性评估中超越了现有方法。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

第一次来请先看这篇文章：【图像拼接（Image Stitching）】关于【图像拼接论文精读】专栏的相关说明，包含专栏使用说明、创新思路分享等（不定期更新）

图像拼接系列相关论文精读

Seam Carving for Content-Aware Image Resizing
As-Rigid-As-Possible Shape Manipulation
Adaptive As-Natural-As-Possible Image Stitching
Shape-Preserving Half-Projective Warps for Image Stitching
Seam-Driven Image Stitching
Parallax-tolerant Image Stitching
Parallax-Tolerant Image Stitching Based on Robust Elastic Warping
SuperPoint: Self-Supervised Interest Point Detection and Description
As-Projective-As-Possible Image Stitching with Moving DLT
Leveraging Line-point Consistence to Preserve Structures for Wide Parallax Image Stitching
Single-Perspective Warps in Natural Image Stitching
Local-Adaptive Image Alignment Based on Triangular Facet Approximation
Image stitching method by multi-feature constrained alignment and colour adjustment
Natural Image Stitching Using Depth Maps
Perception-based seam cutting for image stitching
Stable Linear Structures and Seam Measurements for Parallax Image Stitching