Closed YanHuiGUO closed 3 years ago
It is designed for matching backgrounds. For the best result use a tripod. For small motion handheld, you can preprocess the image for alignment and then pass it through the model. inference-image.py
has --preprocess-alignment
argument.
I just take a picture using my phone to get a background. And at the same position, I take another picture including my upper body. The demo you provided cannot produce a good result. I think the background just has small changes which are very common in real applications and the background is not complicated. Hope you can make it more applicable :)