You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for making this great repository available! I’m using the ViT model, and I’m trying to convert the generated depth map pixel values into real-world units (like meters). I have a specific dataset that I would like to fine-tune the model on, and I’m particularly interested in calculating the distance of some already identified objects in the dataset images.
For reference, I have the ground truth distance of these objects from the camera in meters, and I would like to understand the process of converting the depth values produced by the model to match these real-world distances.
Could you please help clarify:
How can I convert the pixel values from the depth map to real distances (e.g., meters)?
Is there any scaling factor or specific transformation required to go from pixel values to actual physical units?
If not directly possible, could you suggest an approach or workaround to achieve this?
Any pointers or resources would be greatly appreciated! Thanks in advance for your help.
The text was updated successfully, but these errors were encountered:
Thank you for making this great repository available! I’m using the ViT model, and I’m trying to convert the generated depth map pixel values into real-world units (like meters). I have a specific dataset that I would like to fine-tune the model on, and I’m particularly interested in calculating the distance of some already identified objects in the dataset images.
For reference, I have the ground truth distance of these objects from the camera in meters, and I would like to understand the process of converting the depth values produced by the model to match these real-world distances.
Could you please help clarify:
How can I convert the pixel values from the depth map to real distances (e.g., meters)?
Is there any scaling factor or specific transformation required to go from pixel values to actual physical units?
If not directly possible, could you suggest an approach or workaround to achieve this?
Any pointers or resources would be greatly appreciated! Thanks in advance for your help.
The text was updated successfully, but these errors were encountered: