Show HN: MultiMatte, a Promptable Image Background Removal Model
Feyn releases MultiMatte, a promptable background-removal model fine-tuned from Meta's SAM 3 via LoRA, outputting alpha mattes that beat SAM 3 on segmentation benchmarks.
Feyn introduced MultiMatte, a promptable image background-removal model built on Meta's SAM 3 (860M parameters). It modifies only 19.49M parameters (2.27%) using a rank-16 LoRA adapter and replaces binary masks with alpha mattes to handle fuzzy boundaries like hair. On the DIS-VD benchmark it scores 0.901 S-measure versus SAM 3's 0.667, and it improves on SAM 3 across all twelve evaluated splits. Training used 19,953 images for 14,000 steps with focal and Dice loss, and the merged weights are available via the nobg library and a web demo.
- Fine-tunes only 2.27% of SAM 3's 860M parameters with a rank-16 LoRA adapter
- Replaces binary masks with continuous alpha mattes for fuzzy boundaries like hair and translucency
- Improves DIS-VD S-measure from 0.667 to 0.901 and beats SAM 3 on all twelve splits
- Merged adapter shipped in released weights; usable via pip install nobg
- Trained on 19,953 images for 14,000 steps using focal loss plus Dice loss
- Products
- MultiMatteSAM 3NoBg
- Organizations
- MetaFeynThinking Machines Lab
- AI models
- SAM 3MultiMatte
From the original article
4 min read at usefeyn.com
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.
By snyy · usefeyn.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.