[Submitted on 19 Mar 2025 (v1), last revised 27 Oct 2026 (this version, v2)]
Abstract: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 Implicit Bridge Consistency Distillation (IBCD), which enables single-step bidirectional unpaired translation without using adversarial loss. IBCD reformulates consistency distillation by using a diffusion implicit bridge model that connects PF-ODE trajectories between distributions, parametrized on a signed time axis whose sign selects the target domain, so that one network translates in both directions in a single step. 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, and that it extends to brain MRI contrast translation.
Submission history
From: Jong Chul Ye [view email]
[v1] Wed, 19 Mar 2025 09:48:04 UTC (7,749 KB)
[v2] Tue, 27 Oct 2026 09:04:50 UTC (8,821 KB)
