FeyNoBg - SOTA automatic background removal model and training library
Show HN: FeyNoBg – Automatic background removal model and training library
FeyNoBg is a state-of-the-art AI model for automatic background removal, delivering top-tier performance across eight industry benchmarks. It excels in complex scenarios like low contrast, camouflage, and high-resolution 4K/8K images by balancing precise foreground recognition with detailed boundary tracing. Accompanying the model is NoBg, an open-source Python library that simplifies running FeyNoBg or training custom models with a consistent, high-performance interface. Built on BiRefNet and trained on diverse datasets, this toolkit empowers developers to achieve professional-grade image matting effortlessly.
Real images are complex and require deftness in foreground recognition and boundary precision. This was our key insight when training FeyNoBg.
- geooff_
I love seeing this. Background removal is such a core task used in so many systems, I group it in with speech to text in terms of importance.
I love seeing maturity getting pushed in this space. Congratulations to you and the team!
- qingcharles
How does it stack up against Adobe's model? The advantage Adobe has is there are essentially two options: (1) Select Subject (95% of the time will give you the result you want); (2) Select Person (helps in the edge cases).
The issue I have is, what is the subject? For instance, you have a person sat on a couch. You hit Select Subject. Is the subject the person, or the person plus the couch?
With Adobe's when I only want the person, most of the time Select Subject works, and when it doesn't I can pivot to Select Person, but that has its own problem because it won't include props that the subject is holding, only the person and their clothing.
- woadwarrior01
Why extend an MIT licensed model's weights (BiRefNet) and release it under a cc-by-nc-4.0 license?