Hi, I got bad results with the pretrained model, but the results from project website are good. Is it different model on the project website or I have to do some pre-processing? Thank you very much.

hi! i have several panoramic images of the same place and i would like to utilise them together to estimate the layout. or maybe somehow merge the estimated layouts from each image to create the final layout. obviously it’s not part of your project but maybe you can give me some advice/ideas on how to do that? thanks!

Hello everyone,

First of all, thanks for sharing your work, your results are great. I'm trying to replicate them, but I'm facing some issues. First of all, my computer doesn't have a GPU so I tried changing the value of exp_args.device from 'cuda:0' to 'cpu', but I got the following error: RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU. So I added this command, changing this line params = torch.load(args.ckpt) to it params = torch.load(args.ckpt, map_location=torch.device(device)) and I think it should work, but I'm getting the following error (probably unrelated to the device issue):

Traceback (most recent call last):
  File "run_inference.py", line 58, in <module>
    pred_fp_down_man, pred_fp_down_man_pts = LED2Net.DuLaPost.fit_layout(pred_fp_down)
  File "/home/leo/sbdinc/LED2-Net/LED2Net/DuLaPost/layout.py", line 86, in fit_layout
    data_cnt.sort(key=lambda x: cv2.contourArea(x), reverse=True)
AttributeError: 'tuple' object has no attribute 'sort'

My Python version is 3.8.10 and my environment is:

absl-py==1.0.0 attrdict==2.0.1 cachetools==5.0.0 certifi==2021.10.8 charset-normalizer==2.0.11 cycler==0.11.0 fonttools==4.29.1 fvcore==0.1.5.post20220119 google-auth==2.6.0 google-auth-oauthlib==0.4.6 grpcio==1.43.0 idna==3.3 imageio==2.14.1 importlib-metadata==4.10.1 iopath==0.1.9 kiwisolver==1.3.2 Markdown==3.3.6 matplotlib==3.5.1 networkx==2.6.3 numpy==1.22.1 oauthlib==3.2.0 opencv-python==4.5.5.62 packaging==21.3 Pillow==9.0.0 portalocker==2.3.2 protobuf==3.19.4 pyasn1==0.4.8 pyasn1-modules==0.2.8 pylsd-nova==1.2.0 pyparsing==3.0.7 python-dateutil==2.8.2 pytorch3d==0.3.0 PyWavelets==1.2.0 PyYAML==6.0 requests==2.27.1 requests-oauthlib==1.3.1 rsa==4.8 scikit-image==0.19.1 scipy==1.7.3 six==1.16.0 tabulate==0.8.9 tensorboard==2.8.0 tensorboard-data-server==0.6.1 tensorboard-plugin-wit==1.8.1 termcolor==1.1.0 tifffile==2021.11.2 torch==1.10.2 torchaudio==0.10.2 torchvision==0.11.3 tqdm==4.62.3 typing-extensions==4.0.1 urllib3==1.26.8 Werkzeug==2.0.2 yacs==0.1.8 zipp==3.7.0

Any help is appreciated :)

I would like to convert the coordinates of the vertices into the equirectangular coordinates of the panorama, so that I know what are the xy coordinates of the vertices in the original panorama image. Is there a way to do that? Thanks

HI, Thanks for your work. However, I recently found that there are unreasonable situations in calculating IoU, which may lead to errors.

Use image to calculate IoU in your code:

def IoU_2D(pred, gt, dummy_height1=None, dummy_height2=None):
    intersect = np.sum(np.logical_and(pred, gt))
    union = np.sum(np.logical_or(pred, gt))
    iou_2d = intersect / union

    return iou_2d

Calculate IoU using polygon in HorizonNet code:

dt_poly = Polygon(dt_floor_xy)
gt_poly = Polygon(gt_floor_xy)

# 2D IoU
area_dt = dt_poly.area
area_gt = gt_poly.area
area_inter = dt_poly.intersection(gt_poly).area
iou2d = area_inter / (area_gt + area_dt - area_inter)

When I set fp_meters=20 in config file:

Use the floor plan image to calculate IoU2D: 0.8690 Use the floor plan polygon to calculate IoU2D: 0.8722

Use the floor plan image to calculate IoU2D: 0.7491 Use the floor plan polygon to calculate IoU2D: 0.6429

It can be found that there is error in the different calculation.My test results show that the IOU calculated using images is generally greater than that calculated using polygon in Matterport3D's test dataset. I think one reason is that the radius of many layouts stored in the test set exceeds fp_meters, so they are not included in the floor plan image.

I tried to modify fp_meters to a larger value, but the error caused by pixel rounding is enlarged. When I set fp_meters=50 in config file:

Use the floor plan image to calculate IoU2D: 0.8934 Use the floor plan polygon to calculate IoU2D:0.8722

Hi，thanks for your excellent work！I wonder that is there any way to save the rendered image rather than displaying the image on the screen. I am not familiar with QT，can you give me some advice?