基于单应性扩散约束的二步网格优化视差图像对齐
Parallax Image Alignment With Two-stage Mesh Optimization Based on Homography Diffusion Constraints
陈殷齐 1郑慧诚 2严志伟 3林峻宇4
作者信息
- 1. 中山大学计算机学院 广州 510006;季华实验室新型显示技术与装备研究中心 佛山 528000
- 2. 中山大学计算机学院 广州 510006;机器智能与先进计算教育部重点实验室 广州 510006;广东省信息安全技术重点实验室 广州 510006
- 3. 中山大学计算机学院 广州 510006
- 4. 复旦大学计算机科学技术学院 上海 200438
- 折叠
摘要
目前,在带有视差场景的图像对齐中,主要难点在某些无法找到足够匹配特征的区域,这些区域称为匹配特征缺失区域.现有算法往往忽略匹配特征缺失区域的对齐建模,而只将有足够匹配特征区域中的部分单应变换系数(如相似性变换系数)传递给匹配特征缺失区域,或者采用将匹配特征缺失区域转化为有足够匹配特征区域的间接方式,因此对齐效果仍不理想.在客观事实上,位于相同平面的区域应该拥有相同的完整单应变换而非部分变换参数.由此出发,利用单应变换系数扩散的思想设计了一个二步网格优化的图像对齐算法,简称单应扩散变换(Homography diffusion warping,HDW)算法.该方法在第一步网格优化时获得有足够匹配特征区域的单应变换,再基于提出的单应性扩散约束将这些单应变换系数扩散到邻域网格,进行第二步网格优化,在保证优化任务简洁高效的前提下实现单应变换系数的传播与图像对齐.相较于现有的针对视差场景图像对齐算法,所提方法在各项指标上都获得了更好的效果.
Abstract
At present,the main difficulty in the image alignment with parallax scene is in the areas that cannot find sufficient matching features.We call these areas featureless regions.Cutting-edge research on parallax image alignment neglects modeling of regions without matching features.Indirect methods such as transferring partial ho-mography of regions with matching features to featureless regions or transforming featureless regions to regions with matching features have been popularly used,which,however,do not guarantee satisfactory results.In fact,image regions belonging to the same plane should possess the same homography.In this paper,a two-stage mesh optimiza-tion algorithm,homography diffusion warping(HDW),is designed by homography diffusion.In the first stage,ho-mography coefficients of mesh cells in the image regions with matching features are obtained.Then we propagate these homography coefficients to adjacent cells to form homography diffusion constraints,and perform the second stage optimization of the mesh by enforcing the constraints on the premise of ensuring the simplicity and efficiency of the optimization task.Compared with existing image alignment algorithms,the method proposed in this paper achieves better results on all metrics.
关键词
图像对齐/视差场景/网格优化/匹配特征缺失区域Key words
Image alignment/parallax scene/mesh optimization/featureless regions引用本文复制引用
基金项目
国家自然科学基金(61976231)
广东省基础与应用基础研究基金(2019A1515011869)
广州市科技计划项目(201803030029)
出版年
2024
国家科技期刊平台
NSTL
万方数据