A${}^2$BM: Alignment-Aware Bridge Matching for Image-to-Image Translation

• URL: http://arxiv.org/abs/2607.16294v1
• Date: Mon, 13 Jul 2026 08:00:58 GMT
• Title: A${}^2$BM: Alignment-Aware Bridge Matching for Image-to-Image Translation
• Abstract summary: We introduce Alignment-Aware Bridge Matching (A$2$BM), a bridge matching method that leverages image pairs alignment during training.<n>By incorporating alignment scores, the model learns to disentangle true semantic correspondences from misalignment artifacts.<n>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.
• Score: 13.749611763484173
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models [22.803631190636313]
  We introduce Timage, a paradigm that recasts multimodal understanding as an alignment problem solved at the input.<n>The study positions deliberate input reconstruction as a powerful, architecture-neutral lever for strengthening multimodal reasoning.
  arXiv  Detail & Related papers  (2026-06-18T08:40:41Z)
• Unpaired Image-to-Image Translation via a Self-Supervised Semantic Bridge [59.247871132422006]
  Adversarial diffusion and diffusion-inversion methods have advanced unpaired image-to-image translation, but each faces key limitations.<n>We propose the Self-Supervised Semantic Bridge ( SSB), a versatile framework that integrates external semantic priors into diffusion bridge models.<n>Our key idea is to leverage self-supervised visual encoders to learn representations that are invariant to appearance changes but capture geometric structure.
  arXiv  Detail & Related papers  (2026-02-18T18:05:00Z)
• Deterministic Image-to-Image Translation via Denoising Brownian Bridge Models with Dual Approximators [5.59333453533085]
  We propose a denoising Brownian bridge model with dual approximators (Dual-approx Bridge)<n>Our experiments on benchmark datasets demonstrate the consistent and superior performance of Dual-approx Bridge.
  arXiv  Detail & Related papers  (2025-12-29T13:45:21Z)
• How Modality Shapes Perception and Reasoning: A Study of Error Propagation in ARC-AGI [7.226300346775942]
  ARC-AGI and ARC-AGI-2 measure generalization-through-composition on small color-quantized grids.<n>Recent instruction-first systems translate grids into concise natural-language or DSL rules executed in generate-execute-select loops.
  arXiv  Detail & Related papers  (2025-11-11T19:06:41Z)
• EditInfinity: Image Editing with Binary-Quantized Generative Models [64.05135380710749]
  We investigate the parameter-efficient adaptation of binary-quantized generative models for image editing.<n>Specifically, we propose EditInfinity, which adapts emphInfinity, a binary-quantized generative model, for image editing.<n>We propose an efficient yet effective image inversion mechanism that integrates text prompting rectification and image style preservation.
  arXiv  Detail & Related papers  (2025-10-23T05:06:24Z)
• Cross-modal Full-mode Fine-grained Alignment for Text-to-Image Person Retrieval [54.90229711181207]
  Text-to-Image Person Retrieval (TIPR) aims to retrieve the most relevant person images based on a given text query.<n>The key challenge in TIPR lies in achieving effective alignment between textual and visual modalities.<n>We propose FMFA, a cross-modal Full-Mode Fine-grained Alignment framework.
  arXiv  Detail & Related papers  (2025-09-17T07:12:05Z)
• Image-to-Image Translation with Diffusion Transformers and CLIP-Based Image Conditioning [2.9603070411207644]
  Diffusion Transformers (DiT) is a diffusion-based framework for image-to-image translation.<n>DiT combines the denoising capabilities of diffusion models with the global modeling power of transformers.<n>We validate our approach on two benchmark datasets: face2comics, which translates real human faces to comic-style illustrations, and edges2shoes, which translates edge maps to realistic shoe images.
  arXiv  Detail & Related papers  (2025-05-21T20:37:33Z)
• Bi-directional Self-Registration for Misaligned Infrared-Visible Image Fusion [53.60977801655896]
  Acquiring accurately aligned multi-modal image pairs is fundamental for achieving high-quality multi-modal image fusion.<n>We propose a novel self-supervised textbfBi-directional textbfSelf-textbfRegistration framework (textbfB-SR)
  arXiv  Detail & Related papers  (2025-05-11T09:36:25Z)
• Debiasing Vison-Language Models with Text-Only Training [15.069736314663352]
  We propose a Text-Only Debiasing framework called TOD, leveraging a text-as-image training paradigm to mitigate visual biases. To address the limitations, we propose a Text-Only Debiasing framework called TOD, leveraging a text-as-image training paradigm to mitigate visual biases.
  arXiv  Detail & Related papers  (2024-10-12T04:34:46Z)
• Global and Local Alignment Networks for Unpaired Image-to-Image Translation [170.08142745705575]
  The goal of unpaired image-to-image translation is to produce an output image reflecting the target domain's style. Due to the lack of attention to the content change in existing methods, semantic information from source images suffers from degradation during translation. We introduce a novel approach, Global and Local Alignment Networks (GLA-Net) Our method effectively generates sharper and more realistic images than existing approaches.
  arXiv  Detail & Related papers  (2021-11-19T18:01:54Z)
• iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection [48.83883375118966]
  iFAN aims to precisely align feature distributions on both image and instance levels. It outperforms state-of-the-art methods with a boost of 10%+ AP over the source-only baseline.
  arXiv  Detail & Related papers  (2020-03-09T13:27:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.