您的位置:首页 > 其它

Dense Semantic Correspondence

2015-09-27 16:32 363 查看
方法名称

度量相似性的方法

相似性的层面

针对问题

Canonical correspondence

(dis-)similarity metrics

raw pixel intensities

the same underlying scene,brightness constancy assumption

Improved canonical correspondence

Robust (dis-)similarity metrics

raw pixel intensities

the same underlying scene,non-rigid deformations、occlu-

sions、non-global intensity、constrast and colorimet-

ric changes

semantic correspondence

(SIFT Flow)

L1 metric

sparse keypoint

matching,dense SIFT space(sacri
ces some localization accuracy)

across scenes

Ours

Per pixel classifiers

raw pixel intensities(Dense)

across scenes

内容来自用户分享和网络整理,不保证内容的准确性,如有侵权内容,可联系管理员处理 点击这里给我发消息
标签: