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

2025-03-19

AI Summary

Diffusion models and Schrödinger bridge methods for unpaired image-to-image translation suffer from low inference efficiency due to iterative sampling, hindering practical deployment. Method: We propose the first single-step bidirectional translation framework. Its core innovations are: (1) an implicit bridge consistency distillation mechanism that enforces distributional alignment between source and target domains along probability flow ODE (PF-ODE) trajectories; and (2) a distribution-matching distillation scheme with difficulty-aware adaptive weighting, replacing adversarial training and explicit paired supervision. The method eliminates iterative sampling and GAN-based paradigms, requiring only one forward pass. Contribution/Results: On multiple benchmark datasets, our approach achieves state-of-the-art generation quality and FID scores among single-step methods, while accelerating inference by over 100×—significantly advancing the practicality of unpaired image translation.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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/project_page/IBCD/index.html

Problem

• Enables single-step bidirectional unpaired image translation
• Avoids iterative sampling in diffusion-based models
• Improves consistency distillation with adaptive weighting

Innovation

• Implicit Bridge Consistency Distillation for unpaired translation
• Single-step bidirectional translation without adversarial loss
• Diffusion implicit bridge model connects PF-ODE trajectories