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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Suhyeon, Kim, Kwanyoung, Ye, Jong Chul
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910883559505920
author Lee, Suhyeon
Kim, Kwanyoung
Ye, Jong Chul
author_facet Lee, Suhyeon
Kim, Kwanyoung
Ye, Jong Chul
contents 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 at https://hyn2028.github.io/project_page/IBCD/index.html
format Preprint
id arxiv_https___arxiv_org_abs_2503_15056
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation
Lee, Suhyeon
Kim, Kwanyoung
Ye, Jong Chul
Computer Vision and Pattern Recognition
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 at https://hyn2028.github.io/project_page/IBCD/index.html
title Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.15056