Fix overflow and dtype handling in rgblike_to_depthmap (NumPy + PyTorch) #12546
+30
−9
Conversation
This file contains hidden or 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
DN6
reviewed
Oct 27, 2025
| # You may want to cast the final result to uint16, but casting to a | ||
| # larger int type (like int32) is sufficient to fix the overflow. | ||
| # depth_map = depth_map.to(torch.uint16) # Uncomment if uint16 is strictly required | ||
| return depth_map |
There was a problem hiding this comment.
Change looks good. Could we just store the original dtype and cast back once the computation is done.
original_dtype = image.dtype
# perform compute
return depth_map.to(original_dtype)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
This PR fixes a potential overflow bug in
rgblike_to_depthmapwhen computingdepth values from RGB-like depth images.
Changes:
int32before performing the 16-bit combination (*256 +).uint8or small int.uint16casting.Rationale:
The original implementation used
2**8multiplication directly on small integer tensors,which could overflow for high byte values (≥128). The fix ensures safe arithmetic and
consistent return types.
cc @patrickvonplaten @multimodalart @psuraj