google/diffseg
DiffSeg is an unsupervised zero-shot segmentation method using attention information from a stable-diffusion model. This repo implements the main DiffSeg algorithm and additionally includes an experimental feature to add semantic labels to the masks based on a generated caption.
Jupyter NotebookMIT
Stargazers
- 0xdevaliasOpen to opportunities
- andrewncgetcartwheel.com
- awaism47Glasgow, Scotland
- Banguiskode
- bongoleTsukuba, Japan
- boscotba
- brsbyrkIstanbul, Turkey
- elkraneomonstarlab
- erdmannRijksmuseum, University of Amsterdam
- fanyang01
- gaduffl
- gears1992
- jemgold
- jfozard
- jmargetaKardioMe
- JoelChen95
- kawaiibilli
- legel3co
- madhanl6Blue Chip Technologies
- margonzalezfrancoGoogle
- matthew-mcateer5cube Labs
- necusjz@microsoft
- Patrick5088
- PrgckwbThe University of Electro-Comunications
- rasmi@google-org
- satvik007Hypersequent
- seanghayDigital Government Committee
- smb-h@hope-techs
- ssghostArcturus Tech Studio
- syddharthEarth
- taesiriPlanet Mars
- tzmartinSan Francisco, CA
- veeragoniAmazon
- vinxvShanghai
- wxxb789
- zsoltkiraGeorgia Institute of Technology