riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-02 19:21:31 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

[ViTMatte] Add resources (#26317)

Browse Source 
Add resource
This commit is contained in:
NielsRogge 2023-09-26 07:06:38 +02:00 committed by GitHub
parent ace74d16bd
commit a09130feee
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 14 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
docs/source/en/model_doc/vitmatte.md
View File

@ -10,12 +10,12 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
specific language governing permissions and limitations under the License.
-->
# VitMatte
# ViTMatte
## Overview
The VitMatte model was proposed in [Boosting Image Matting with Pretrained Plain Vision Transformers](https://arxiv.org/abs/2305.15272) by Jingfeng Yao, Xinggang Wang, Shusheng Yang, Baoyuan Wang.
VitMatte leverages plain [Vision Transformers](vit) for the task of image matting, which is the process of accurately estimating the foreground object in images and videos.
The ViTMatte model was proposed in [Boosting Image Matting with Pretrained Plain Vision Transformers](https://arxiv.org/abs/2305.15272) by Jingfeng Yao, Xinggang Wang, Shusheng Yang, Baoyuan Wang.
ViTMatte leverages plain [Vision Transformers](vit) for the task of image matting, which is the process of accurately estimating the foreground object in images and videos.
The abstract from the paper is the following:
@ -28,6 +28,17 @@ Tips:
This model was contributed by [nielsr](https://huggingface.co/nielsr).
The original code can be found [here](https://github.com/hustvl/ViTMatte).
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/vitmatte_architecture.png"
alt="drawing" width="600"/>
<small> ViTMatte high-level overview. Taken from the <a href="https://arxiv.org/abs/2305.15272">original paper.</a> </small>
## Resources
A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with ViTMatte.
- A demo notebook regarding inference with [`VitMatteForImageMatting`], including background replacement, can be found [here](https://github.com/NielsRogge/Transformers-Tutorials/tree/master/ViTMatte).
## VitMatteConfig