79148937

Date: 2024-11-01 17:44:50
Score: 2
Natty:
Report link

Storing the intermediate image in 8-bit or even 16-bit per channel will make you lose way too much precision, maybe 32-bit float will allow you to get a meaningful amount of high frequency detail back, but even that's definitely far from perfect if my math is right.

Reasons:
  • Low length (0.5):
  • No code block (0.5):
  • Single line (0.5):
  • Low reputation (0.5):
Posted by: damian101