Show HN: FeyNoBg – Automatic background removal model and training library

In one line

FeyNoBg beats or matches the current leaders across eight benchmarks. Alongside the model, we’re releasing NoBg. The library we used to train it.

Opening excerpt

Research · field note FeyNoBg: A SOTA Model For Background Removal Authors Hafedh Hichri, Shreyash Nigam Affiliation Feyn Labs Published July 21, 2026 Reading time 8 min We’re introducing FeyNoBg, a state-of-the-art model for automatic background removal. Across eight benchmarks, it posts the best published S-measure on four and comes within 2% of the leader on the rest.

We’re also releasing NoBg, the library we used to train our model. Use NoBg to run FeyNoBg or train your own background removal model.

Both are open source. Download FeyNoBg on Hugging Face , or build with NoBg on GitHub .

In your computer, images are stored as grids of pixels. The goal of a background removal algorithm is to predict an opacity value for each pixel such that background pixels become transparent, foreground pixels remain opaque, and boundary pixels become translucent.

(Excerpted from the original; full article via the source link below.)

This story hit the Hacker News front page today (70 points / 20 comments, via usefeyn.com). Our Tech Radar aggregates daily signals on AI engineering, backend architecture and DevOps — browse the related services and further reading below, or get in touch with our team.