Task
Other
V
hustvl/vitmatte-small-composition-1k
Other·hustvl· 1.4M· 54
transformers
apache-2.0
25.8M params
arxiv:2305.15272license:apache-2.0region:us
ViTMatte model trained on Composition-1k. It was introduced in the paper ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers by Yao et al. and first released in this repository.
# pull & run locally
pip install mlforge-sdk && mlforge pull hustvl/vitmatte-small-composition-1k
pip install mlforge-sdk && mlforge pull hustvl/vitmatte-small-composition-1k
Model details
Provider
hustvl
Framework
transformers
Parameters
25.8M
Size
197 MB
License
apache-2.0
Downloads
1.4M
Likes
54
Paper
arXiv:2305.15272
Updated
2024-03-29
About hustvl/vitmatte-small-composition-1k
ViTMatte model trained on Composition-1k. It was introduced in the paper ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers by Yao et al. and first released in this repository.