wujinhu1999
wujinhu1999
Output during training：   The configuration I use is dtu_mlp_fullres_allviews.conf, which is a dataset around the brain without a mask image. I did not run scannet_to_monosdf.py, I changed img_res...
Taking scan65 as an example, the pair.txt I generated is different from the original data set. Will this have any impact on the final result? Looking forward to your reply....
Hello author, I would like to ask how to obtain these files(000000_sfm_points.txt、000001_sfm_points.txt、000002_sfm_points.txt···)? I can only generate cameras.txt, images.txt and points3D.txt using colmap.Looking forward to your reply.
Regarding the training of DTU with 3 viewing angles mentioned in your paper, I would like to ask if you finally used all the pictures in scan65, that is, 49...
I'm not using distributed training, I changed the code slightly, the command I run on the terminal is:python training/exp_runner.py --local_rank=2 --conf confs/dtu_mlp_3views.conf --scan_id 65，and then：  After a period of...
Hello author, I would like to ask if I do not use distributed training and only use one GPU for training, will it affect the results?
Hello author, thank you for your great work! I would like to ask why my mean_d2s and mean_s2d are so different? Also, what happens when I get a visualize error...
Thank you for your great work. https://github.com/autonomousvision/monosdf/issues/85#issue-1951881310 Taking scan65 as an example, the pair.txt I generated is different from the original data set. Will this have any impact on the...
Hello authors, thank you for your great work! I encountered some problems while training neus-acc. There is a lot of noise around the reconstructed object. How to remove this? Are...
Hello authors, thank you for your great work! When I use the command 'ns-train geo-volsdf --pipeline.model.sdf-field.inside-outside False --vis wandb --experiment-name geo-volsdf-dtu65 sdfstudio-data --data data/dtu/scan65 --load-pairs True' and 'ns-train geo-unisurf --pipeline.model.sdf-field.inside-outside...