3D Mesh Generation from DSM Images from Sat-NeRF output #35
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
module import error solved
Recently, an issue was encountered during the execution of the training script, specifically a TypeError: 'module' object is not callable. This error was traced back to the metrics.py file within the ssim function. The problem arose because the alias ssim_ for the kornia.losses.ssim function was mistakenly treated as a callable function, leading to the TypeError. To resolve this issue, the following changes were made: In the metrics.py file, the import statement from kornia.losses import ssim as ssim_ was replaced with from kornia.losses import ssim as kornia_ssim. The ssim function definition was updated from return torch.mean(ssim_(image_pred, image_gt, 3)) to return torch.mean(kornia_ssim(image_pred, image_gt, 3)). These modifications correctly import and utilize the ssim function from the kornia.losses module, resolving the TypeError. With these changes, the training script can now execute without encountering this specific error, ensuring the SSIM calculation is handled correctly and allowing for smoother execution and accurate performance metrics. To incorporate this fix, update the import statement and the ssim function definition in the metrics.py file as described above. Re-running the training script after these modifications will ensure proper functionality.
Creating ply file using DSM image map
Python script that converts Digital Surface Model (DSM) data into high-quality 3D mesh files. Utilizing the Open3D library and the power of NVIDIA A100 GPUs, the script efficiently processes DSM images to produce .ply and .obj files, suitable for 3D visualization and further processing
Python script that converts Digital Surface Model (DSM) data into high-quality 3D mesh files. Utilizing the Open3D library and the power of NVIDIA A100 GPUs, the script efficiently processes DSM images to produce .ply and .obj files, suitable for 3D visualization and further processing.
|
https://github.com/tersite1/DSMtoPLY This is the Project page for more explanation. And I added height parameter for better 3D creation. sample |
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Dear Centre Borelli,
I hope this message finds you well. I'm senior undergraduate student of Yonsei University, Civil & Environmental engineering. First and foremost, thank you for your incredible work on the Sat-NeRF and making it as open-source on GitHub. It has been an invaluable resource for those of us who are interesting in working with geospatial data and 3D modeling.
After using your model to generate DSM images, I found myself in need of a method to convert these DSMs into 3D mesh files that could be easily visualized and used in other applications. To address this need, I developed a script that takes your DSM outputs and converts them into high-quality 3D meshes, outputting the results in both .ply and .obj formats. The script leverages Open3D for point cloud processing, normal estimation, and Poisson surface reconstruction, with the added benefit of GPU acceleration where available.
Given that this script complements your existing work, I thought it might be a useful addition to your repository. I’ve included it in this pull request, along with clear documentation on how to use it.
What I did :
I believe this functionality could be a valuable extension for users who are looking to further utilize the DSM images generated by your model. I have so much interests about Geospatial data processing and NeRF, so I would be honored if you would consider merging this pull request into your repository.
Please feel free to reach out if you have any questions or need any adjustments. I’m also open to any feedback or suggestions you might have.
Thank you again for your outstanding contributions to the field.
Best regards,
This is the target image that I used for 3D data creation and outputs are below.
Thank you.