| title | license | tags | pretty_name | models | datasets | emoji | colorFrom | colorTo | sdk | sdk_version | app_file | pinned | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Open Remove Background Model (ormbg) |
apache-2.0 |
|
Open Remove Background Model |
|
|
💻 |
red |
red |
gradio |
4.29.0 |
hf_space/app.py |
false |
Join our Research Discord Group!
This model is a fully open-source background remover optimized for images with humans. It is based on Highly Accurate Dichotomous Image Segmentation research.
python ormbg/inference.py
Install dependencies:
conda env create -f environment.yaml
conda activate ormbg
Replace dummy dataset with training dataset.
python3 ormbg/train_model.py
I started training the model with synthetic images of the Human Segmentation Dataset crafted with LayerDiffuse. However, I noticed that the model struggles to perform well on real images.
Synthetic datasets have limitations for achieving great segmentation results. This is because artificial lighting, occlusion, scale or backgrounds create a gap between synthetic and real images. A "model trained solely on synthetic data generated with naïve domain randomization struggles to generalize on the real domain", see PEOPLESANSPEOPLE: A Synthetic Data Generator for Human-Centric Computer Vision (2022).
- Expand dataset with synthetic and real images
- Research on state of the art loss functions
- Created synthetic dataset with 10k images, crafted with BlenderProc
- Removed training data created with LayerDiffuse, since it lacks the accuracy needed
- Improved model performance (after 100k iterations):
- F1: 0.9888 -> 0.9932
- MAE: 0.0113 -> 0.008
- Scores based on this validation dataset
- Added P3M-10K dataset for training and validation
- Added AIM-500 dataset for training and validation
- Added PPM-100 dataset for training and validation
- Applied Grid Dropout to make the model smarter