---
title: ormbg
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/ormbg"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/ormbg.md"
repository: AI-ModelScope/ormbg
last_updated: 2024-10-02
license: apache-2.0
pipeline_tag: image-segmentation
tasks:
  - image-segmentation
library_name:
  - onnx
  - pytorch
frameworks:
  - pytorch
downloads: 3461
stars: 2
tags:
  - segmentation
  - "remove background"
  - background
  - background-removal
  - Pytorch
---

# ormbg

> ormbg - AI-ModelScope 在 ModelScope 开源的模型。Open Remove Background Model (ormbg)

AI-ModelScope/ormbg 是 ModelScope 魔搭社区上的image-segmentation模型，采用 apache-2.0 许可。

- **Repository**: AI-ModelScope/ormbg
- **License**: apache-2.0
- **Tasks**: image-segmentation
- **Tags**: segmentation, remove background, background, background-removal, Pytorch
- **Downloads**: 3461
- **Stars**: 2
- **Last updated**: 2024-10-02

Source: https://www.modelscope.cn/models/AI-ModelScope/ormbg

---

# Open Remove Background Model (ormbg)

[>>> DEMO <<<](https://huggingface.co/spaces/schirrmacher/ormbg)

Join our [Research Discord Group](https://discord.gg/YYZ3D66t)!

![](examples/image/image01_no_background.png)

This model is a **fully open-source background remover** optimized for images with humans. It is based on [Highly Accurate Dichotomous Image Segmentation research](https://github.com/xuebinqin/DIS).

## Inference

```
python ormbg/inference.py
```

## Training

Install dependencies:

```
conda env create -f environment.yaml
conda activate ormbg
```

Replace dummy dataset with [training dataset](https://huggingface.co/datasets/schirrmacher/humans).

```
python3 ormbg/train_model.py
```

# Research

I started training the model with synthetic images of the [Human Segmentation Dataset](https://huggingface.co/datasets/schirrmacher/humans) crafted with [LayerDiffuse](https://github.com/layerdiffusion/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)](https://arxiv.org/pdf/2112.09290).

### Next steps:

- Expand dataset with synthetic and real images
- Research on state of the art loss functions

### Latest changes (26/07/2024):

- Created synthetic dataset with 10k images, crafted with [BlenderProc](https://github.com/DLR-RM/BlenderProc)
- Removed training data created with [LayerDiffuse](https://github.com/layerdiffusion/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](https://drive.google.com/drive/folders/1Yy9clZ58xCiai1zYESQkEKZCkslSC8eg)

### 05/07/2024

- Added [P3M-10K](https://paperswithcode.com/dataset/p3m-10k) dataset for training and validation
- Added [AIM-500](https://paperswithcode.com/dataset/aim-500) dataset for training and validation
- Added [PPM-100](https://github.com/ZHKKKe/PPM) dataset for training and validation
- Applied [Grid Dropout](https://albumentations.ai/docs/api_reference/augmentations/dropout/grid_dropout/) to make the model smarter