jbhuang0604 / selfexsr Goto Github PK
View Code? Open in Web Editor NEWSingle Image Super-Resolution from Transformed Self-Exemplars (CVPR 2015)
Home Page: https://sites.google.com/site/jbhuang0604/publications/struct_sr
Single Image Super-Resolution from Transformed Self-Exemplars (CVPR 2015)
Home Page: https://sites.google.com/site/jbhuang0604/publications/struct_sr
Hello,
The cvpr paper is an excellent work and I tried to run the code. However, it appears errors as follows.
??? Undefined variable "vision" or class "vision.ShapeInserter".
Error in ==> sr_extract_plane>sr_detect_plane_from_vp at 179
shapeInserter = vision.ShapeInserter('Shape', 'Lines','BorderColor', 'White');
Error in ==> sr_extract_plane at 48
modelPlane = sr_detect_plane_from_vp(vpData, img, opt);
Error in ==> sr_demo at 38
modelPlane = sr_extract_plane(filePath.dataPath, filePath.imgFileName, opt);
Error in ==> sr_demo_batch at 63
imgHiRes = sr_demo(filePath, opt);
It seems some code were missing or I made some mistakes to miss something. Would you help me solve it .Thank you very much! @jbhuang0604
The matlab code in sr_extract_plane.m invoking source/EdgeDetectTest.exe generates only partial info
vx vy vz score numLines
-0.99157554 0.12952947 0.00024355 650.54 47
0.76044877 -0.64939690 -0.00115497 488.17 39
-0.43647291 0.89971575 0.00172559 331.19 31
But expected is 4KB file as present in "cache\vpdetection\text\img_100_SRF_2_LR-vanishingpoints.txt"
The start , end and length of lines in 3 sets not present.
Tried in x64 machine.
Behavior in matlab code and CMD for the source/EdgeDetectTest.exe is same.
Any suggestion?
Thanks !
I got an error using the 2015 version
hi all!
the code needs to execute EdgeDetectTest.exe , so it needs Windows SO. Is there a workaround or can anyone give the exe source code so that I can compile it on linux? If not, anyone could give me another solution?
tnx
Hi, thanks for ur sharing!!!
I was wondering whether u had the x3 downsapled urban100 dataset?
The links corresponding to datasets 'Set 5' and 'Set 14' give a 404 error. It would be great if you could share the dataset for open testing.
Hi,
First of all, thank you for the excellent work and code! I was trying to evaluate my own method with you quantification script. But there seems to be an error in the function compute_difference.m
At some point in the code the function tries to use variable warpedImage:
% Compute Structural similarity index (SSIM index)
45 % =========================================================================
46 [ssim, ~] = ssim_index(imgt, warpedImage);
…
49 % Compute information fidelity criterion (IFC)
50 % =========================================================================
51 ifc = ifcvec(imgt, warpedImage);
But warpedImage was not defined before. I am guessing it should just be replaced with 'im' such that the code becomes
% Compute Structural similarity index (SSIM index)
45 % =========================================================================
46 [ssim, ~] = ssim_index(imgt, im);
…
49 % Compute information fidelity criterion (IFC)
50 % =========================================================================
51 ifc = ifcvec(imgt, im);
Is this correct, or did you intend to have another preprocessing step which produces warpedImage?
Thanks again for the great work!
Cheers
the links of datasets were not opened
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.