aiyb1314/genpercept

GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

Guangkai Xu,   Yongtao Ge,   Mingyu Liu,   Chengxiang Fan,   Kangyang Xie,   Zhiyue Zhao,   Hao Chen,   Chunhua Shen,  

Zhejiang University

HuggingFace | arXiv

🔥 Fine-tune diffusion models for perception tasks, and inference with only one step! ✈️

📢 News

• 2024.3.10: Release arXiv v1 paper.
• 2024.3.15: Release arXiv v2 paper, with supplementary material.
• 2024.4.6: Release inference code and depth checkpoint weight of GenPercept in the GitHub repo.
• 2024.4.7: Add HuggingFace App demo.

🖥️ Dependencies

conda create -n genpercept python=3.10
conda activate genpercept
pip install -r requirements.txt
pip install -e .

🚀 Inference

Download the pre-trained depth model depth_v1.zip from BaiduNetDisk (Extract code: z938) or Rec Cloud Disk. Put the package under ./weights/ and unzip it, the checkpoint will be stored under ./weights/depth_v1/.

Then, place images in the ./input/ dictionary, and run the following script. The output depth will be saved in ./output/.

sh scripts/inference_depth.sh

For surface normal estimation, run the following script:

bash scripts/inference_normal.sh

Thanks to our one-step perception paradigm, the inference process runs much faster. (Around 0.4s for each image on an A800 GPU card.)

📖 Recommanded Works

• Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation. arXiv, GitHub.
• GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image. arXiv, GitHub.
• FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models. arXiv, GitHub.

🏅 Results in Paper

Depth and Surface Normal

Dichotomous Image Segmentation

Image Matting

Human Pose Estimation

🎫 License

For non-commercial use, this code is released under the LICENSE. For commercial use, please contact Chunhua Shen.

🎓 Citation

@article{xu2024diffusion,
  title={Diffusion Models Trained with Large Data Are Transferable Visual Models},
  author={Xu, Guangkai and Ge, Yongtao and Liu, Mingyu and Fan, Chengxiang and Xie, Kangyang and Zhao, Zhiyue and Chen, Hao and Shen, Chunhua},
  journal={arXiv preprint arXiv:2403.06090},
  year={2024}
}