用量子桥接加速图像翻译，计算量不到原来十分之一
Latent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation
- 用随机微分方程建模分布间转换，分解向量场提升效率
- 仅需少量计算即可实现与主流方法相当的无配对图像转换效果
- 适合追求快速生成且无需成对数据的应用场景
扩散模型（DMs）在图像生成和数据反演方面表现强大，已催生高效无配对图像到图像（I2I）翻译算法。然而，这些方法通常需要大量神经函数评估（NFE），限制了实际应用。本文提出利用薛定谔桥（SBs），即在最小运输成本下连接分布的随机微分方程（SDE）。分析其概率流常微分方程（ODE）形式后，发现可将向量场分解为源预测器、目标预测器和噪声预测器的线性组合。受此启发，我们提出潜空间薛定谔桥（LSBs），通过预训练的Stable Diffusion近似SB ODE，设计适当的提示优化与变量变换公式，实现训练与推理分布间的匹配。实验表明，该方法在无监督设置下实现具有竞争力的I2I翻译，且计算成本仅为以往基于扩散模型方法的极小部分。
原文摘要 · Abstract (English)
Diffusion models (DMs), which enable both image generation from noise and inversion from data, have inspired powerful unpaired image-to-image (I2I) translation algorithms. However, they often require a larger number of neural function evaluations (NFEs), limiting their practical applicability. In this paper, we tackle this problem with Schrodinger Bridges (SBs), which are stochastic differential equations (SDEs) between distributions with minimal transport cost. We analyze the probability flow ordinary differential equation (ODE) formulation of SBs, and observe that we can decompose its vector field into a linear combination of source predictor, target predictor, and noise predictor. Inspired by this observation, we propose Latent Schrodinger Bridges (LSBs) that approximate the SB ODE via pre-trained Stable Diffusion, and develop appropriate prompt optimization and change of variables formula to match the training and inference between distributions. We demonstrate that our algorithm successfully conduct competitive I2I translation in unsupervised setting with only a fraction of computation cost required by previous DM-based I2I methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。