hanjoonwon

How can i get background removed result?

2

I don't want to reconstruct the background, just the object. Which pipeline option should I use to achieve the desired result?

Warning: FullyFusedMLP is not supported for the selected architecture 37. Falling back to CutlassMLP. For maximum performance, raise the target GPU architecture to 75+.

2

 MY gpu is rtx 2060 CUDA_ARCHITECTURES=90;89;86;80;75;70;61;52;37 build correctly how can i solve this error??

Is it possible to add an option to get the foreground image mask during the data process or to add the image mask by myself?

Is it possible to use the NEUS model directly in the NERFSTUDIO environment with the data processed by NERFSTUDIO?

Is there a good method for mesh quality?

5

Is there a good way to improve the mesh quality? ns-train nerfacto --pipeline.model.predict-normals True --data output/scan --pipeline.datamanager.train-num-rays-per-batch 2000 I'm currently doing this, but I don't know if the Poisson mesh...

how to improve mesh quailty?

1

I trained with these pipelines, but the surface mesh quality was poor. How can I get a better quality mesh? ns-train nerfacto --pipeline.model.predict-normals True --data output/scan --pipeline.datamanager.train-num-rays-per-batch 2000

image process match laptop and desktop results are different

2

https://drive.google.com/drive/folders/1Q9zSM8sCsQ4n-6QKl4GEujuznx-abxvh?usp=sharing my images are here   If my desktop has a high match, why does my laptop have a much lower match? In addition to this image, I also...

cant connect web viewer

2

windows 10, anaconda I don't know if it's because I moved Anaconda's startup to eDrive, but I can't get into the web viewer. How do I fix it? 

Does reducing num face improve mesh quality?

1

i trained with ns-train nerfacto --pipeline.datamanager.train-num-rays-per-batch 2048 --max-num-iterations 100000 --vis viewer --data E:\deeplearning\nerfstudio\out\owl2 nerfstudio-data and then export meshes ns-export poisson --load-config outputs\owl2\nerfacto\2024-01-29_180036\config.yml --output-dir exports/owl2 --target-num-faces 40000 --num-pixels-per-side 2048 --num-points 1000011...

 got this error how can i solve this?