BackgroundMattingV2

BackgroundMattingV2 copied to clipboard

How to use MattingRefine?

6

I got the following error message after input the src and bgr imge. Please help me, thanks. Traceback (most recent call last): File "./Matting/inference_images.py", line 131, in pha, fgr, _,...

Willy-NotSpe

This algorithm has very good effect, but I can't download the pretrained model and weights from google drive, can you put the model on baidu drive?

songdanjgs

视频抠图换背景测试可以，但残影比较明显，请问如何解决？另外所换背景是只能图片吗，可否用视频？

2

owlsaea

Hi, I am confused about how can you collect no-person image (background). When I open the webcam of Zoom, both I and the background are in capture region. 

LemonTwoL

貌似在自己的视频上测试，感觉效果不是很好啊

4

感谢伟大的作者，做了很有意义的事。我这边看了作者的论文，写的也很清楚透彻。 我试了下代码，包含mobilenetv3和resnet50，在自己的视频上做测试，但是感觉效果不是很好，尤其是边缘部分，经常会缺失或者多出一些小块，请问是我哪些地方没注意到吗?

tengshaofeng

There is an unprocessed hole in the center of the screen when the camera is running

1

python inference_webcam.py --model-type mattingrefine --model-backbone mobilenetv2 --model-checkpoint "pytorch_mobilenetv2.pth" --model-backbone-scale 0.5 --resolution 1280 720

YX-003

Real Time Performance

15

Thanks for such a nice work. I have a question related to real time inferences on the video input data.I have tested the resnet50 backbone model on the 1080p resolution...

NaeemKhan333

Improving performance of video inference and increase GPU utilization

2

Two improvements are made in this contribution: 1. Removed repeated copying of background image to GPU memory, minimizing the effect of a memory bandwidth bottleneck 2. Increased GPU utilization by...

h9419

執行inference_images.py 完後 沒有顯示任何圖片？

6

執行inference_images.py 完後 沒有顯示任何圖片？請問有人也是一樣嗎？執行完顯示出Directory /home/user/matting/img_output already exists. Override? [Y/N]: y 但在資料夾中卻沒有顯示？

yoyoyin0902

Questions about training

8

I have a question. Background input is required in sample and paper, so do I need to input background during training? I see no background images in the publicly available...

xiaobao886