Open Remove Background Model (ormbg)
This model is a fully open-source background remover optimized for images with humans. It is based on Highly Accurate Dichotomous Image Segmentation research. The model was trained with the synthetic Human Segmentation Dataset, a dataset crafted with LayerDiffuse and IC-Light.
This model is similar to RMBG-1.4, but with open training data/process and commercially free to use.
Inference
python utils/inference.py
Training
The model was trained on a NVIDIA GeForce RTX 4090 (10.000 iterations) with the Human Segmentation Dataset which was created with LayerDiffuse and IC-Light.
Want to train your own model?
Checkout Highly Accurate Dichotomous Image Segmentation code:
git clone https://github.com/xuebinqin/DIS.git
cd DIS
Follow the installation instructions on https://github.com/xuebinqin/DIS?tab=readme-ov-file#1-clone-this-repo. Download or create some data (like this) and place it into the DIS project folder.
I am using the folder structure:
- training/im (images)
- training/gt (ground truth)
- validation/im (images)
- validation/gt (ground truth)
Apply this git patch for setting the right paths and remove normalization of images:
git apply dis-repo.patch
Start training:
cd IS-Net
python train_valid_inference_main.py
Export to ONNX (modify paths if needed):
python utils/pth_to_onnx.py
Research
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).
Currently I am doing research how to close this gap. Latest research is about creating segmented humans with LayerDiffuse and then apply IC-Light for creating realistic light effects and shadows.
Support
This is the first iteration of the model, so there will be improvements!
If you identify cases were the model fails, upload your examples!
Known issues (work in progress):
- close-ups: from above, from below, profile, from side
- minor issues with hair segmentation when hair creates loops
- more various backgrounds needed