search

zouchuhang / LayoutNet

Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image"
http://openaccess.thecvf.com/content_cvpr_2018/papers/Zou_LayoutNet_Reconstructing_the_CVPR_2018_paper.pdf
MIT License
419 stars 93 forks source link

some poor images cannot make it #17

Closed limchaos closed 6 years ago

limchaos commented 6 years ago

Hi,really good work! when I evaluated some images at optimization step,it's not work any more, I mean most images I used can make it,but except some of them ,for example, like this one below, can you help me:D

Undefined function or variable 'cor_fn_t'.
Error in samplingPanoBox (line 38)
            line_can(line_n+1:end,score_id(line_id)) =cor_fn_t(2*score_id(line_id),1);

zouchuhang commented 6 years ago

@limchaos Probably your number of "cor_id" been sent to the samplingPanoBox function is less than 8 (not all corners are detected). You need to check it first. If so, you can lower the hyper-parameter(value of MinPeakProminence) of function "findpeaks" in getIniCor.m to get full corners.

limchaos commented 6 years ago

I see,thanks for your help