Getting landmark coordinates

Question

Getting landmark coordinates

richliao opened this issue 7 years ago · comments

Dear Ziwei,

Awesome and interesting work!

Do you mind shed some lights on what is purpose of the statement -get_orig_coordinate = @(p)((p+0.5)*224-repmat([offset(2),offset(1)]',[pipline.num_points,1]))/scale;?

I can not relate this to the paper, particularly (p+0.5)*224. I don't have matlab so I won't be able to debug the value but when I run pyCaffe those values of landmarks came out of stage 1 forward are very small, same as pseudo labels (all lower than 0.01). Any explanations will be greatly appreciated! Thanks.

sijie yan · Answer 1 · Wed Mar 01 2017 21:34:16 GMT+0800 (China Standard Time)

Dear richliao,
Thanks for your interest in our work.
We normalized landmarks to [-0.5, 0.5] in training process.
And we used images of 224*224 for training model.
This operation is just for projecting normalized landmarks to absolute coordinate frame.

Richard Liao · Answer 2 · Sat Mar 04 2017 06:54:22 GMT+0800 (China Standard Time)

Thanks for the explanation, Ziwei!

Can you further elaborate a bit how to convert from a vector (1 dimension) to x and y coordinates which are 2 dimension? Further, I don't see any input box, are you assuming the box is the full size of the image (224x224)? Thanks much.

sijie yan · Answer 3 · Sat Mar 04 2017 22:19:10 GMT+0800 (China Standard Time)

the meaning of a output vector is [x1, y1, x2, y2 ....]

Yes, and the matlab script would resize images to 224*224 before testing.

Ziwei Liu · Answer 4 · Wed May 03 2017 17:45:48 GMT+0800 (China Standard Time)

@richliao Yes, the inputs to our Deep Fashion Alignment (DFA) are clothes bounding boxes. We treat this detection and cropping procedure as pre-processing and don't include it in this codebase. But you can definitely find bounding box annotations in the DeepFashion dataset.