Pinned
Introducing Vision Banana🍌: an image generator that achieves SOTA on segmentation, depth prediction, and surface normal estimation 🚀
🖼️Project page: vision-banana.github.io
📜Technical report: arxiv.org/abs/2604.20329
🧵👇
Valentin Gabeur
@vgabeur
- Here is a thread with some precisions regarding our evaluation of Vision Banana on the SA-Co/gold segmentation benchmark. [1/n] 🧵👇In this age of PR, it's common to see bombastic claims like "beating SAM3". However I take issue with this chart which is quite dishonest IMHO. I would have expected more academic honesty from researchers I deeply respect @sainingxie, @vgabeur, @jalayrac @jon_barron. A quick 🧵
- Next-level referring expression segmentation with Gemini 2.5 🤯Gemini 2.5 introduces conversational image segmentation for AI, enabling advanced visual understanding through object relationships, conditional logic, and in-image text. developers.googleblog.com/en/conversatio…
- Proud to present our work on getting Gemini 2.5 to predict segmentation masks in images! This allows for the next level of complexity in language prompting 🚀Gemini 2.5 introduces conversational image segmentation for AI, enabling advanced visual understanding through object relationships, conditional logic, and in-image text. developers.googleblog.com/en/conversatio…
