The quality of texture is very poor

[a1445605672]

I used volsdf for training.
Here is my parameter setting：
The parameters are consistent with the recommendations, but with one modification
--pipeline.model.sdf-field.bias 0.3
Below is my mesh：

The situation after texture mapping is as follows:

Why do my texture look so weirdly colored?

[hanjoonwon]

Can i ask what parameters were used for training? Currently I don't get a good output like yours, it comes out in a weird shape...

+I got better result by disable depth loss

[superhero177]

Hello, I found that the extracted texture image in the texture extraction section is pure black. Have you encountered a similar situation before?
my trian
ns-train neus-facto \ --pipeline.model.sdf-field.use-grid-feature True \ --pipeline.model.sdf-field.hidden-dim 256 \ --pipeline.model.sdf-field.num-layers 2 \ --pipeline.model.sdf-field.num-layers-color 2 \ --pipeline.model.sdf-field.use-appearance-embedding True \ --pipeline.model.sdf-field.geometric-init True \ --pipeline.model.sdf-field.inside-outside False \ --pipeline.model.sdf-field.bias 0.8 \ --pipeline.model.sdf-field.beta-init 0.3 \ --pipeline.datamanager.train-num-images-to-sample-from -1 \ --trainer.steps-per-eval-image 5000 \ --pipeline.model.background-model none \ --vis wandb \ --experiment-name kitchen_sensor_depth-neus \ --pipeline.model.sensor-depth-l1-loss-mult 0.1 \ --pipeline.model.sensor-depth-freespace-loss-mult 10.0 \ --pipeline.model.sensor-depth-sdf-loss-mult 6000.0 \ --pipeline.model.mono-normal-loss-mult 0.05 \ --pipeline.datamanager.train-num-rays-per-batch 2048 \ --machine.num-gpus 1 \ sdfstudio-data \ --data path_in \ --include_sensor_depth True \ --skip_every_for_val_split 30
my extra mesh
ns-extract-mesh --load-config /home/sdfstudio/outputs/1227_shubaotest4/neus-facto/2024-12-27_205131/config.yml --output-path /home/sdfstudio/outputs/1227_shubaotest4/meshes/shubao.ply

with texture