annci62

train blender datas using ./script/benchmarking/launch_train_blender.sh and export pointcloud, but the pointcloud output is incorrect and has many white points.

4

**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior: ns-train Lego in nerf_synthetic and ns-rander, but output is error,...

When run "python BakedSDF2FBX.py glbfile", error!

1

step: 1) python launch.py --config configs/bakedsdf-blender.yaml --gpu 0 --train --exp_dir /home/disk2/out/torch-bakedsdf/ dataset.root_dir=/home/disk2/data/nerf_synthetic/lego/ name=nues-blender-lego 2) python export.py --exp_dir /home/disk2/out/torch-bakedsdf/nues-blender-lego/@20231123-153121/ --output-dir /home/disk2/out/torch-bakedsdf/nues-blender-lego/@20231123-153121/ 3) python BakedSDF2FBX.py /home/disk2/out/torch-bakedsdf/nues-blender-lego/@20231123-153121/nues-blender-lego.glb output： 

cmd: python main.py /media/arcvideo/disk2/data/bag/test5/nerf2mesh/ --wo rkspace bag_color_sdf -O --bound 1 --scale 0.8 --dt_gamma 0 --stage 0 --mcubes_reso 768 --env_reso 768 --sdf --lambda_tv 1e-8 return: