A${}^2$BM: Alignment-Aware Bridge Matching for Image-to-Image Translation
For practitioners of image-to-image translation, A2BM provides a principled solution to the common problem of misaligned training data, improving translation fidelity without requiring perfectly aligned pairs.
A2BM introduces alignment-aware bridge matching for image-to-image translation, handling weakly aligned training pairs by incorporating alignment scores to improve translation fidelity. It consistently outperforms GAN-, diffusion-, and Schrödinger bridge-based baselines on tasks like cross-sensor super-resolution and unsupervised domain adaptation.
Paired image-to-image translation underpins a wide range of computer vision tasks, including image editing, sensor translation, and domain adaptation. Bridge matching and flow matching have recently emerged as powerful frameworks, extending diffusion models to arbitrary source and target distributions. However, their standard formulations assume perfectly aligned training pairs, treating all source-target correspondences as equally reliable. In practice, real-world applications often involve weakly aligned pairs due to changes of acquisition conditions, including e.g. asynchronous captures, different illuminations, or misregistration. In this work, we introduce Alignment-Aware Bridge Matching (A${}^2$BM), a bridge matching method that leverages image pairs alignment during training. By incorporating alignment scores, the model learns to disentangle true semantic correspondences from misalignment artifacts. At inference time, we use the alignment score as a control variable over translation fidelity, with strongly aligned outputs obtained when prompting the model with the highest alignment score. We validate A${}^2$BM on both controlled synthetic experiments and on challenging real-world tasks, including cross-sensor super-resolution and pixel-space unsupervised domain adaptation. In all settings, A${}^2$BM consistently improves translation fidelity over strong GAN-, diffusion-, and Schr{ö}dinger bridge-based baselines, establishing alignment conditioning as a principled solution for image translation models with weakly aligned data.