neural-rgbd-surface-reconstruction
neural-rgbd-surface-reconstruction copied to clipboard
Official implementation of the CVPR 2022 Paper "Neural RGB-D Surface Reconstruction"
@dazinovic Hello, can you provide a thin_geometry configuration file, there is no thin_geometry.txt file in the configs folder, because thin_geometry requires less memory, it can be duplicated on a machine...
Thank you for your excellent work, I used [https://cvg.cit.tum.de/data/datasets/intrinsic3d](url) tomb data and my own data when the final reconstruction of the effect of the problem appeared in the figure. I...
can you offer a demo for python optimize.py --config configs/.txt
Hello Unless I'm not understanding anything but I can't see anywhere how to run the program to have a result like video or something. However when I run this command...
@dazinovic Hello,Thanks for this great job。 because thin_geome. txt is missing in configs file, I tried to configure it by myself following other data sets, but the effect was very...
Hi @dazinovic , Thanks for your great work! Based on the pose conversion you provided #2 , T0 @ scannet_pose @ T1, I want to make sure that the coordinate...
hi, many thanks for your great works! I tried to run the transform_mesh.py and cull_mesh.py scripts on the breakfast_room data on remote server. But I get a error with the...
Hi, Thanks for sharing you great work! I found that neural-rgbd performs well in estimating the camera poses, so I wonder if you can share the estimated camera poses on...
Hi, firstly thanks so much for this amazing work. Now I finished all the preparation steps and started running "optimize.py". 1. After traininng I will get a reconstruction mesh which...