Questions about encoding?

Thank you for sharing your excellent work！
But I have a question about your implementation of hash encoding. In model/encodings.py, you wrote this code to achieve the allocation of multiple resolutions:
per_level_scale = np.exp2(np.log2(desired_resolution / n_levels) / (n_levels - 1))
But I found that the settings for this instant-ngp are not the same, you did not use N_ Min for calculation. May I ask how to understand this code?
I would be very grateful if you could explain this code

Hi @tql-code, thank you for your question. I apologize for the confusion caused by the code snippet you mentioned. There is a typo, and the correct code should be:

Co-SLAM/model/encodings.py

Line 33 in 1049b2b

    
           per_level_scale = np.exp2(np.log2(desired_resolution  / base_resolution) / (n_levels - 1))

Since the base_resolution and n_levels were both set to 16 in our setting, this typo did not cause any difference and thus went unnoticed during the development. Sorry for that.

I appreciate you bringing it to my attention. I have now fixed the issue and pushed the latest version to the GitHub repository. If you have any further questions or concerns, please feel free to let me know:)