Hi, thank you for releasing this great work!
I have a question about the output values of the lotus-depth-g-v2-1-disparity model.
Could you please clarify:
Are the predicted relative depth (or disparity) values normalized to the range [0, 1], or
Do they represent affine-invariant / relative depth (i.e., up to a global scale and shift)?
I'm trying to understand how to interpret the raw output for visualization and comparison with other depth models (e.g., Marigold, DepthMaster, MiDaS).
Any clarification would be greatly appreciated.
Thank you! 🙏