New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
How to improve image matting accuracy #24
Comments
Hi, thanks for your attention. Can you share some failure cases with me? |
@mosvlad |
Thanks for replying @ZHKKKe |
@zzmao |
@ZHKKKe What should be the approach to improve the performance of the backbone model, i.e., the MobileNetV2? |
@alan-ai-learner Q2: can you tell me what type of data you used for training? Q3: Can you please tell me the approach to train on our own data set? |
Thanks, but in # BackgroundMattingV2 they are using a different approach, in # BackgroundMattingV2 we need to pass two images one with the subject and the other is without a subject (only background). But in MODnet we need to pass only one image. |
@alan-ai-learner |
@ZHKKKe Do you think there will be an improvement in accuracy by combining supervised training with the estimation of foreground color? |
@ZHKKKe got it |
@newjavaer |
@ZHKKKe Why do you think there are more errors in semantic estimation? |
Many erros are caused by recongnizing cloth as a part of person. Maybe can be improved by giving some penalty during the training. I have collected some person matting data from several semantic datasets, and new CELEBA-MASK-HQ dataset, it may imporve the result. |
@QuantumLiu By adding some background images as negative samples to the training? |
@newjavaer
|
@QuantumLiu The solution proposed by @newjavaer is also great. We do not consider the negtive samples during training since it is a engineering problem. |
Please feel free to reopen this question if you have any questions. |
Has anyone tried replacing Low-Resolution Branch backbone. How is the result? |
@syfbme The performance may be further improved. Please refer to https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.3/contrib/Matting |
Hi,
Thanks for this great project. I tried your colab for image matting, it looks like the boundary is not clear enough for some inputs(also the one in Github readme).
Is there anyway to improve image matting accuracy?
The text was updated successfully, but these errors were encountered: