Latent Bridge Matching (LBM)

This repository is the official implementation of the paper LBM: Latent Bridge Matching for Fast Image-to-Image Translation.

DEMO space

Abstract

In this paper, we introduce Latent Bridge Matching (LBM), a new, versatile and scalable method that relies on Bridge Matching in a latent space to achieve fast image-to-image translation. We show that the method can reach state-of-the-art results for various image-to-image tasks using only a single inference step. In addition to its efficiency, we also demonstrate the versatility of the method across different image translation tasks such as object removal, normal and depth estimation, and object relighting. We also derive a conditional framework of LBM and demonstrate its effectiveness by tackling the tasks of controllable image relighting and shadow generation.

Setup

To be up and running, you need first to create a virtual env with at least python3.10 installed and activate it

With venv

python3.10 -m venv envs/lbm
source envs/lbm/bin/activate

With conda

conda create -n lbm python=3.10
conda activate lbm

Then install the required dependencies and the repo in editable mode

pip install --upgrade pip
pip install -e .

Inference

We are internally exploring the possibility of releasing the pre-trained models.

License

This code is released under the Creative Commons BY-NC 4.0 license.

Citation

If you find this work useful or use it in your research, please consider citing us

@article{chadebec2025lbm,
      title={LBM: Latent Bridge Matching for Fast Image-to-Image Translation}, 
      author={Clément Chadebec and Onur Tasar and Sanjeev Sreetharan and Benjamin Aubin},
      year={2025},
      journal = {arXiv preprint arXiv:2503.07535},
}