32 6

Peng Zheng

ZhengPeng7

https://zhengpeng7.github.io

AI & ML interests

None yet

Recent Activity

updated a model 5 days ago

ZhengPeng7/BiRefNet

updated a model 5 days ago

ZhengPeng7/BiRefNet_HR-matting

updated a model 5 days ago

ZhengPeng7/BiRefNet_HR

View all activity

Organizations

None yet

ZhengPeng7's activity

updated 13 models 5 days ago

updated a Space 15 days ago

200

BiRefNet Demo

🐠

Extract and mask subjects from images

published a model 16 days ago

ZhengPeng7/BiRefNet_HR-matting

Image Segmentation • Updated 5 days ago • 1.1k • 1

New activity in ZhengPeng7/BiRefNet 19 days ago

Added BiRefNet v2 to Background Removal Arena

#14 opened 29 days ago by

tdurbor

Inference Endpoint

#5 opened 7 months ago by

iamrobotbear

Update README.md

#13 opened about 2 months ago by

artemtumch

published a model 24 days ago

ZhengPeng7/BiRefNet_512x512

Image Segmentation • Updated 5 days ago • 545 • 2

posted an update 24 days ago

Post

2493

We just released the [BiRefNet_HR]( ZhengPeng7/BiRefNet_HR) for general use on higher resolution images, which was trained with images in 2048x2048. If your images are mostly larger than 1024x1024, use BiRefNet_HR for better results! Thanks to @Freepik for the kind support of H200s for this huge training.

HF Model: ZhengPeng7/BiRefNet_HR.
HF Demo: ZhengPeng7/BiRefNet_demo, where you need to choose General-HR and set high resolution.
PyTorch weights & ONNX: in Google Drive and the GitHub release.

Here is a comparison between the results of the original one and the new HR one on HR inputs:

And, the performance of this new HR one and the previous one trained in 1024x1024 on val set: