基于隐式桥一致性蒸馏的单步双向无配对图像翻译
Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation
AI总结：
针对现有无配对图像翻译方法迭代采样、落地难的问题，提出隐式桥一致性蒸馏框架IBCD，结合扩散隐式桥与两项改进，实现单步双向无配对翻译，在基准数据集上达SOTA性能。
摘要：
自CycleGAN提出以来，无配对图像到图像翻译取得了显著进展。然而，基于扩散模型或薛定谔桥的方法由于其迭代采样的特性，尚未在实际应用中得到广泛采用。为解决这一挑战，我们提出了一种名为Implicit Bridge Consistency Distillation（IBCD，隐式桥一致性蒸馏）的新型框架，它无需使用对抗损失即可实现单步双向无配对翻译。IBCD通过采用连接不同分布间PF-ODE轨迹的扩散隐式桥模型，对一致性蒸馏进行了扩展。此外，我们还引入了两项关键改进：1）面向一致性蒸馏的分布匹配，2）基于蒸馏难度的自适应加权方法。实验结果表明，IBCD在基准数据集上仅需单步生成即可达到当前最优性能。项目页面见https://hyn2028.github.io/project_page/IBCD/index.html
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
