Manuel Dahnert
Manuel Dahnert
The model was trained on a RTX 2080Ti with 11GB memory. Few things you can check: - Increase the number of iterations of lower resolutions are trained (LEVEL_ITERATIONS_64, LEVEL_ITERATIONS_128) before...
Hi, I got the same issue. Clone the repo and building it locally resolved the issue for me.
Hi all, sorry for the delay - I just returned from travelling. I will have a look at this issue the next days. Thanks
Hi, can you post the complete name of the sample? The segmentation data is very sparse, so it is very likely, that it contains a lot of zeros. To verify...
Hi, sorry for the delay. To get data in a Total3D-like format, i.e. per-object bounding boxes, it is easier to parse the per-object information directly from the original 3D-Front .json...
Hi, could you fill out the original Matterport3D Terms-Of-Service and send it to [email protected] Afterwards I can send you the data.
I had the same problem. In the download_wieghts.py, Line 79, you can replace `info=spaghetti_airplanes` with `info=spaghetti_chairs_large` to download the respective weights.
Hi, thanks for sharing this great work! I have the same question: Could you release the pix3d dataset splits? Thanks a lot!
See email. I'll leave it open until we have resolved it.