sdfstudio
sdfstudio copied to clipboard
A Unified Framework for Surface Reconstruction
I have been preprocessing datasets from distinct captures (moments in time and camera sizes). I could only acquire this by using `hloc`, obtaining the `images.bin` and `cameras.bin`. However there is...
 How can I improve these results? I have already tried changing bbox and near-far. What parameters should I tune? The images only have foreground with white background. Command used:...
**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior: 1. Go to '...' 2. Click on '....' 3. Scroll...
  ![Uploading image.png…]() @niujinshuchong I trained with ns-train neus --pipeline.datamanager.train-num-rays-per-batch 2048 --pipeline.model.sdf-field.inside-outside False\ --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-grid-feature False \ --pipeline.model.sdf-field.bias 0.3 --pipeline.model.sdf-field.beta-init 0.3 --pipeline.model.background-model mlp\ --pipeline.model.sdf-field.use-appearance-embedding...
Hello, training nerfacto with the dtu dataset doesn't really work with the following command `ns-train nerfacto --vis tensorboard --trainer.max-num-iterations 60000 --timestamp nerfacto sdfstudio-data --data data/dtu/scan105. `  Did anyone have...
Hi, I captured a video length 1 minutes, then train with neus-facto. One frame in the video like this  The toy is with white sword. I trained...
https://drive.google.com/drive/folders/1Q9zSM8sCsQ4n-6QKl4GEujuznx-abxvh?usp=drive_link  i trained with ns-train neus --pipeline.datamanager.train-num-rays-per-batch 2048 --pipeline.model.sdf-field.inside-outside False\ --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-grid-feature False\ --pipeline.model.sdf-field.bias 0.3 --pipeline.model.sdf-field.beta-init 0.3 --pipeline.model.background-model mlp \ --pipeline.model.sdf-field.use-appearance-embedding True\ --trainer.steps-per-eval-image...
## Describe the bug I used DTU images(1600,1200) to build sdfstudio(meta_data.json) from colmap, tested neus-facto, and got a poor results. ## Here is my process: **1. I ran the _colmap(hloc)_...
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...