ysalaun / linesfm Goto Github PK

DETECT LINES AND COMPUTE DESCRIPTORS
OpenCV Error: Assertion failed (ssize.width > 0 && ssize.height > 0) in resize, file /root/opencv-3.4.0/modules/imgproc/src/resize.cpp, line 4044
terminate called after throwing an instance of 'cv::Exception'
what(): /root/opencv-3.4.0/modules/imgproc/src/resize.cpp:4044: error: (-215) ssize.width > 0 && ssize.height > 0 in function resize

I have no idea what should I do according to the error.

Dear @ySalaun , thanks for provide this LineSfM code.
Lately I test this code. I found I got the different results compared to the result presented in your paper 《Robust SfM with Little Image Overlap》. I tested the sample images following the steps of the instruction: LSD_MULTISACALE--VANISHING_POINT--LINE_MATCHING--CALIBRATION--RECONSTRUCTION, but the dence.refined.mesh.ply only contains four 3D points.

ply
format ascii 1.0
element vertex 4
property float x
property float y
property float z
property uchar red
property uchar green
property uchar blue
element face 0
property list uint8 int32 vertex_indices
end_header
0.0106194 -0.189911 0.14482 50 255 50
0.803659 -0.126331 0.723105 50 255 50
1.567 -0.0715306 1.42358 50 255 50
2.56536 -0.0378929 1.85199 50 255 50

I notice that the openMVG folder is where I should save my detection with my openMVG, so I wonder if I got the wrong detection of the openMVG.

Hi,
From the paper "Robust SfM with Little Image Overlap", you have said,
"Our approach thus leverages on lines for pose estimation and reconstruction, although it also exploits points when available."

I'd like to know how to compute camera pose what if there are not any feature points at all.
Currently, I have trouble at the CALIBRATION stage. I find that your code must read points descriptor and points match in the main_calibration.cpp. So I have to delete these two lines. After that, I get the wrong camera pose:
1 -0 -nan
0 1 -0
nan 0 1
7.7018e-311 7.7018e-311 -1

And also, I find some thread in another closed issue, you said ,"If you want to use line only, you should use trifocal methods",
I'd like to know how to turn on the trifocal model?

Best regards,
Jin

Hello, @ySalaun!

Thank you for your great job on line-based SfM. I'm reading your code and have some doubts.

From line 246 to line 284 in LineSfM/CALIBRATION/scale_uniformization.cpp, you make a repartition among directions. But the code seems useless.

Firstly, variables dir_left, dir_right, proj_left, proj_right and found are defined in the function computeCoplanarCts. They are never used after line 284.

Secondly, though you modify cluster_left and cluster_right, which can be used beyond this function, the function computeCoplanarCts is only used once and these 2 parameters make no sense.

Maybe you wanted to do something, but you forgot?

And actually I don't know what this repartition do. Would you mind explaining it to me? Thank you.

Looking forward to your reply.

Sincerely,
Jim

since narrow perspective cannot ensure the triplet. we choose 3 panoramas. but I know the theory cannot support the vps in panoramas. but it genrated some results.

Though the result looks like it is not that bad. so does it mean some conincident?

All the dataset can be download below.
https://drive.google.com/open?id=14eerqQs2g0LudnXJsMCDBsMoo0g4sQOl

Dear @ySalaun , thank you for share such a nice LineSfM code.
Recently，I read your paper 《Robust SfM with Little Image Overlap》， I am interested in the indoor dataset of the paper, but I don't know how to download it, can you provide it to me ?

Hi,
I have run the full pipeline as your readme said.
The result of reconstruction stage seems uncorret, as followed.

I cant see the structure of the original image from these reconstructed planes.
But I can see the 3d structure from the openMVG pipeline

And I'd like to know how to get the 3d lines from the ply file?

Can you have a look at my reconstruction log?
reconstruction.log

Hi, I use the TEST_IMAGE and use openMVG detections, but the CALIBRATION output this:
4
0000 /home/holy/source/com-InteriorModeling/LineSFMTestData/origin/0000.png
0001 /home/holy/source/com-InteriorModeling/LineSFMTestData/origin/0001.png
0002 /home/holy/source/com-InteriorModeling/LineSFMTestData/origin/0002.png
0003 /home/holy/source/com-InteriorModeling/LineSFMTestData/origin/0003.png
reading intrinsic parameters
reading global poses
computing relative poses
LOAD DETECTIONS AND MATCHES
COMPUTE POSES
PROCESSED IN 3.84876
images 0 and 1
Error in rotation : 120
Error in translation : nan
images 1 and 2
Error in rotation : 120
Error in translation : nan
images 2 and 3
Error in rotation : 120
Error in translation : nan
AVERAGE RESULTS:
Rotation: 120
Translation: nan

What this Error?

Hi,
I've found the problem about the issue #4 . The result of line matching is terrible. There unexpectedly exist corresponding line pairs between two irrelevant images.

There are some warnings during line match stage, and missing line match files during calibration

Is Line Band Descriptor not as robust as sift point descriptor?
Or the threshold of ransac stage in matching is not correct?