en
0.25
0.5
0.75
1.25
1.5
1.75
2
Rolling Guidance Filter
Published on Oct 29, 20144089 Views
Images contain many levels of important structures and edges. Compared to masses of research to make filters edge preserving, finding scale-aware local operations was seldom addressed in a practical w
Related categories
Chapter list
Rolling Guidance Filter00:00
Images00:10
Image filter00:15
Image Filtering00:34
An Important Steam: Edge Preserving00:45
Edge preserving may not work for pet beatification01:08
Edge preserving also fails the batman01:28
Many tiny contents are strong01:39
What better characters them?01:57
Scale in Computer Vision02:06
Scale + Image filter = ?02:28
Example 102:34
Example 202:40
Scale-Aware Filtering02:52
Related Work - 103:09
Related Work - 203:26
Related Work - 303:33
Interesting Fact03:41
Main Idea04:11
Our Scale-aware Filter04:46
Step 1: Small Structures Removal05:04
Step 2: Edge Recovery05:12
Rolling Guidance05:59
Guidance for the 1st iteration06:12
Guidance for the 2nd iteration06:18
Guidance for the 3rd iteration06:21
Guidance for the 5th iteration06:25
Small structures are removed. Large structure are NOT blurred.06:35
Why does rolling guidance work?06:44
Small Structure06:49
Large Structure07:50
Joint Bilateral Filter08:22
Input vs. Guidance Image08:57
Rolling Guidance Filter09:11
Comparison09:27
Result Comparison09:33
Performance Comparison - 109:49
Performance Comparison - 210:21
Results & Application10:27
Texture Removal - 110:32
Texture Removal - 210:39
Texture Removal - 310:44
Halftone Image - 110:55
Halftone Image - 211:14
Small Text Removal11:23
Virtual Edge Detection - 111:35
Virtual Edge Detection - 212:05
Natural Images12:34
Determining Scales12:53
Multi-Scale Filtering - 113:08
Multi-Scale Filtering - 213:45
Summary14:15
Code Avalible Online14:40
Thank You14:52