sunset1995/HorizonNet
Pytorch implementation of HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation.
PythonMIT
Issues
- 0
- 0
I want to save the generated model as an obj+mtl file and import it into Blender. May I ask which UV coordinate values to pass in?
#43 opened by Robintjhb - 7
Finetuned model
#10 opened by glacierwl - 1
Magic number in decoder fc layer
#34 opened by walsvid - 0
max of 4 walls to model
#41 opened by LitalEfraim103 - 1
- 2
Why z0 is set to be 50?
#36 opened by Gaowz112 - 1
- 0
- 0
Missing model weights
#37 opened by johnwlambert - 0
- 0
error while using customized data
#35 opened by ChikkathotadappaAshwin-zz - 6
If inferenced on the non-rectified image (no preprocessing but the wall in the image is vertical), the corners are not correct
#22 opened by HiPupilxD-Hao - 3
- 2
Export GLTF File
#25 opened by Allvirus - 0
Point Cloud Registration
#33 opened by rimoune - 1
3D IoU evaluation bug in `eval_general.py`
#17 opened by sunset1995 - 1
Need output as .gltf format
#32 opened by PriteshGujarati - 0
Getting error while training the model
#30 opened by jitender-code - 0
release resnet50_rnn__mp3d.pth
#29 opened by xuyongzhi - 0
Is it possible to translate the coordinates of a point from point cloud to the coordinates of the same point in the panorama?
#27 opened by dimabendera - 0
Question about ordering corner coordinates
#26 opened by palver7 - 2
the result seems to be inversed
#24 opened by shi-yan - 2
- 1
What is the definition of tol? Why are you setting tol=abs(0.16 * z1 / 1.6) in inference.py?
#7 opened by Hanoch666 - 0
Error in inference.py
#21 opened by muachichi - 2
Customized dataset
#20 opened by muachichi - 1
Multiple pano images?
#16 opened by seankovacs - 4
- 2
finetune model
#12 opened by github163sl - 8
is there some model adjustment in it?
#11 opened by ayj12345 - 4
- 2
boundary training loss encounters impulse
#1 opened by lijing1996 - 1
Non-2x1 images
#6 opened by truszko1 - 3
Something about Dataloader
#4 opened by limchaos - 2
- 1
How to train the network in three GPUs
#3 opened by XGBoost