图像修复三:Image Completion using Planar Structure Guidance

提出一种自动利用中间层结构线索指导图像修复的方法。通过估计平面投影参数并发现平面上的平移规律,将这些信息转化为低级修复算法的软约束,定义了补丁偏移和转换的先验概率。在未检测到平面时,回退到基线正面平行图像修复算法。

Image Completion using Planar Structure Guidance.2014, ACM SIGGRAPH.

项目主页:https://sites.google.com/site/jbhuang0604/publications/struct_completion

ppt下载:https://uofi.app.box.com/s/2x1a8ja976wxhsglvggz

code:https://github.com/jbhuang0604/StructCompletion

A method for automatically guiding patch-based image completion using mid-level structural cues. Our method first estimates planar projection parameters, softly segments the known region into planes, and discovers translational regularity within these planes. This information is then converted into soft constraints for the low-level completion algorithm by defining prior probabilities for patch offsets and transformations. Our method handles multiple planes, and in the absence of any detected planes falls back to a baseline fronto-parallel image completion algorithm.

PPT 中首先对修复作了一个分类,如下图:


该方法基于的模型:


添加中间导向特征:





移除结果与结论:






评论 15
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值