Re:Show HN: OfferGridAI – side-by-side comparison of real es...
by lysecret on Friday January 02, 2026 @01:41PM
(#46467917)
Hmm so that post also links back to segmentation done by structured outputs? (Though here not even enforcing the structure)
https://ai.google.dev/gemini-api/docs/image-understanding#se...
Re:Show HN: OfferGridAI – side-by-side comparison of real es...
by simonw on Friday January 02, 2026 @02:13PM
(#46468233)
It's not supported by Gemini 3: https://ai.google.dev/gemini-api/docs/gemini-3#migrating_fro...
> Image segmentation: Image segmentation capabilities (returning pixel-level masks for objects) are not supported in Gemini 3 Pro or Gemini 3 Flash. For workloads requiring native image segmentation, we recommend continuing to utilize Gemini 2.5 Flash with thinking turned off or Gemini Robotics-ER 1.5.
But the bounding box stuff might work well enough in Gemini 3 to handle this case as well.