PlaneNet
PlaneNet copied to clipboard
PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image
Thank you for your valuable work!The planes_scannet_train.tfrecords link does not work, I hope you can update the link or send the training data set to my email。My email is [email protected],Thank...
Hello @art-programmer , I wanted to know in dat_prep/parser.py why the offset is squared planes *= pow(planesD, 2) cause accordind to my understanding PlanesD alread holds the value of the...
There are depth output and semantation output. In the paper, the method also outputs plane parameters and 3D mesh models. Is this because these outputs are disabled in the predict.py...
Cannot download the file planes_scannet_train.tfrecords: * Google Drive link doesn‘t work, there seems to be a quota that has been exceeded. * The alternative box.com link doesn‘t work as the...
Hi! I'm having some troubles running the code parse.py in the folder data_preparation. In the function readMesh, you do "plane=fitPlane(XYZ)" but fitPlane is not defined. How can i solve this...
After running: ` $ python predict.py --customImageFolder="/scratch/chaitanyakharyal/images/" ` I got this error: ` Traceback (most recent call last): File "predict.py", line 18, in from train_planenet import build_graph File "/home/chaitanyakharyal/planenet/PlaneNet/train_planenet.py", line...
Hi , when I run the evaluate.py , There is only " gt" result , no "prediction " result .What code should I modify to get the "prediction" result !...
Hi, I have read your paper, but I'm confused about the way the planes are labeled from 1 to 10 (if 10 planes are found), and I haven't got a...
Hi, @DRAhmadFaraz, I have got the predictions of PlaneNet, but the per-pixel recall seems to be lower than that in the paper. Can you reproduce the evaluation in the paper?...
Hi, Your work is very good and I am very interested. But when i run the following code: python evaluate.py --dataFolder=". /data" --numImages=760 --methods=2000000 --numOutputPlanes=10 ;The final result appears index...