What type of study is this?

This is a Experimental Study study.

October 8, 2025Open Access

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

Key Points

IBCD demonstrates significant improvements in unpaired image-to-image translation and operates without adversarial loss.
The framework shows state-of-the-art results on benchmark datasets with a single generation step.
Two enhancements include a distribution matching approach and an adaptive weighting method to optimize distillation.
Experimental findings highlight the framework's potential for broader applications despite past limitations of diffusion models.

Abstract

Unpaired image-to-image translation has seen significant progress since the introduction of CycleGAN. However, methods based on diffusion models or Schr\"odinger 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 at https: //hyn2028. github. io/projectₚage/IBCD/index. html

Read Full Paperexternally

Mark Helpful

Bookmark

Relay

View Full Paper