graphto3d icon indicating copy to clipboard operation
graphto3d copied to clipboard

Code for ICCV 2021 paper Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes using Scene Graphs

Results 8 graphto3d issues
Sort by recently updated
recently updated
newest added

Hi, I guess there is a problem at [here](https://github.com/he-dhamo/graphto3d/blob/1db83c79036e9baab8a35a238c22f3222c8e43b7/model/graph.py#L108C9-L108C100). According to your paper, after g1 (MLP layer), the calculation of edge is finished. So, if I want to do multiple...

Hi, The download links in download_metadata_3rscan.sh are not working. If you can let us know what the different files are, we can also create the text files from the json...

Hi, I have a question regarding [obj_pointset = self.norm_tensor(obj_pointset, denormalize_box_params(tight_boxes[i])](https://github.com/he-dhamo/graphto3d/blob/809e314762213b743ecad0bd2df64cfd95901e5b/dataset/dataset.py#L484) Could you please help me out? It seems like you assigned a number from 0 to 24 to angle(bbox[6]), right?...

Thanks for your awesome work. I trained the model following the instruction of README. But the quality of visualization is different from your results. Left figure is result from my...

![image](https://user-images.githubusercontent.com/50651190/190069610-e6ac30dc-e277-4d06-9705-fa101b052bf7.png) ![image](https://user-images.githubusercontent.com/50651190/190069664-3ffd6f01-26ba-4e2e-a00e-805abb6b82dc.png) ![image](https://user-images.githubusercontent.com/50651190/190069727-0012ed25-b6e2-437c-b292-8bbd1f084ed1.png) Hello,I tried to run the evaluate_vaegan.py to visualize 3D scene in "meshes", and there is some bug ,I want to know what do I need to modify...

Add current directory "./" in statements

Hey, was getting the following error on Colab with Python 3.7.12 ``` ERROR: Invalid requirement: 'cloudpickle=0.5.3' (from line 3 of requirements.txt) Hint: = is not a valid operator. Did you...

Dear authors, when I train the code with the pytorch==1.10, I meet some problem, during the loss backward procedure