Show HN: MultiMatte, a Promptable Image Background Removal Model
Researchers from Feyn Labs have introduced MultiMatte, an image background removal model built on Meta's SAM 3 architecture. By using low-rank fine-tuning, the model improves segmentation accuracy for complex, fuzzy-edged objects like hair or translucent materials.
Why it matters
Advancements in promptable image segmentation significantly lower the barrier for high-quality content creation and automated visual editing.
Research · field note MultiMatte: Keep What You Want, Cut the Rest Authors Hafedh Hichri, Shreyash Nigam Affiliation Feyn Labs Published September 10, 2026 Reading time 5 min Contents From Segmentation to Matting Training MultiMatte Results Run MultiMatte Acknowledgements We’re introducing MultiMatte, a background removal model you can aim with words. MultiMatte keeps the object you name and removes everything else.
Try MultiMatte on your own images at usefeyn.com/multimatte .
MultiMatte is built on SAM 3 ( Meta, 2025 ). We used low-rank fine-tuning to modify 19.49M of its 860M parameters. That update touches only 2.27% of the model weights, yet MultiMatte improves substantially on image segmentation. On the DIS-VD benchmark, it scores a 0.901 S-measure against SAM 3’s 0.667.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in