Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation

Unpaired image-to-image translation has seen significant progress since the introduction of CycleGAN. However, methods based on diffusion models or Schrödinger bridges have yet to be widely adopted in real-world applications due to their iterative sampling nature. To address this challenge, we propose a novel framework, Implicit Bridge Consistency Distillation (IBCD), which enables single-step bidirectional unpaired translation without using adversarial loss. IBCD extends consistency distillation by using a diffusion implicit bridge model that connects PF-ODE trajectories between distributions. Additionally, we introduce two key improvements: 1) distribution matching for consistency distillation and 2) adaptive weighting method based on distillation difficulty. Experimental results demonstrate that IBCD achieves state-of-the-art performance on benchmark datasets in a single generation step. Project page available atthis https URL

@article{lee2025_2503.15056,
  title={ Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation },
  author={ Suhyeon Lee and Kwanyoung Kim and Jong Chul Ye },
  journal={arXiv preprint arXiv:2503.15056},
  year={ 2025 }
}