MLI
MLI copied to clipboard
Novel View Synthesis with multiplane/multilayer representation: CVPR2022, WACV2023
Hi, I was curious how the depth percentiles p_x in dataset.csv are computed? I tried projecting the colmap points into each camera and then computing percentiles using all visible points,...
Hello, When I run this command: torchrun \--standalone \--nproc_per_node=1 \bin/train.py \--config configs/tblock4_train.yaml \--output-path train_outputs The following error appears: (train) clientadmin@clientadmin-Precision-3660:~/likang/MPI/MLI_new$ torchrun \--standalone \--nproc_per_node=1 \bin/train.py \--config configs/tblock4_train.yaml \--output-path train_outputs 2023-11-10 16:19:31.813855:...
Hi, I wonder what's the data convention after parsing the pose file following: https://github.com/SamsungLabs/MLI/blob/f6503c0535dc340c60c60f3085fe79198d56e963/lib/datasets/sword.py#L213C21-L213C105 Is it OpenCV or Blender style? Many thanks!
In google colab, I had the error `NotImplementedError: A UTF-8 locale is required. Got ANSI_X3.4-1968` when calling `! rm -rf '/usr/local/share/jupyter/nbextensions/google.colab/multi-layer-viewer/mli_scene'` cell. I has been fixed by adding before ```...
Hi, I'm really inspired by the idea in the paper: Stereo Magnification with Multi-Layer Images. It seems like the model structure described in this code does not match the paper...
Great work! I met problems when I runned the render.py and render_val_dataset.py. It could not fint pretrained/stereo_layers/stereo_layers.yaml. Besides, the pretrained/download.sh was empty and could you please explain the detailed information...
Hello, I have been following your project and I must say the team has done an excellent job so far. However, I have encountered an issue with the model training....
Thank you for your patience and enthusiasm to answer my question. If the virtual camera I want to generate MLI images is parallel to the ground, where can I modify...