This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
Yeah I just figured it out right before seeing this. Filtering made all the difference. Once I removed all the points marked by the mask from recoverPose, removed the negative z points and far away points the result looks as expected.
| | 2 | No.2 Revision |
Yeah I just figured it out right before seeing this. Filtering made all the difference. Once I removed all the points marked by the mask from recoverPose, removed the negative z points and far away points the result looks as expected.expected. Thanks for your help.
| | 3 | No.3 Revision |
Yeah I just figured it out right before seeing this. Filtering made all the difference. Once I removed all the points marked by the mask from recoverPose, removed the negative z points and far away points then after rescaling by 10x the result looks as expected. Thanks for your help.
| | 4 | No.4 Revision |
Yeah I just figured it out right before seeing this. Filtering made all the difference. Once I removed all the points marked by the mask from recoverPose, removed the negative z points and far away points then after rescaling by 10x the result looks as expected. Thanks for your help.
| | 5 | No.5 Revision |
Yeah I just figured it out right before seeing this. Filtering made all the difference. Once I removed all the points marked by the mask from recoverPose, removed the negative z points and far away points then after rescaling by 10x the result looks as expected. Thanks for your help.
| | 6 | No.6 Revision |
Filtering made all the difference. Once I removed all the points marked by the mask from recoverPose, removed the negative z points and the far away points then after (cv::norm(p - origin) > 200 ) things improved. After rescaling by 10x the result looks as expected. Thanks for your help.
| | 7 | No.7 Revision |
Filtering made all the difference. Once I removed all the points marked by the mask from recoverPose, the negative z points and the far away points then (cv::norm(p (cv::norm(point - origin) > 200 ) things improved. After rescaling by 10x the result looks as expected. Thanks for your help.
| | 8 | No.8 Revision |
Filtering made all the difference. Once I removed all the points marked by the mask from recoverPose, the negative z points and the far away points then (cv::norm(point - origin) > 200 ) then things improved. After rescaling by 10x the result looks as expected. Thanks for your help.
