DBMSolver: A Training-free Diffusion Bridge Sampler for High-Quality Image-to-Image Translation

• URL: http://arxiv.org/abs/2605.05889v1
• Date: Thu, 07 May 2026 08:59:05 GMT
• Title: DBMSolver: A Training-free Diffusion Bridge Sampler for High-Quality Image-to-Image Translation
• Abstract summary: Diffusion-based image-to-image (I2I) translation excels in high-fidelity generation but suffers from slow sampling in state-of-the-art DBMs.<n>We introduceolver, a training-free sampler that exploits the semi-linear structure of DBM's underlying SDE and ODE.<n>This reduces NFEs by up to 5x while boosting quality.
• Score: 21.779024754526322
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion-based image-to-image (I2I) translation excels in high-fidelity generation but suffers from slow sampling in state-of-the-art Diffusion Bridge Models (DBMs), often requiring dozens of function evaluations (NFEs). We introduce DBMSolver, a training-free sampler that exploits the semi-linear structure of DBM's underlying SDE and ODE via exponential integrators, yielding highly-efficient 1st- and 2nd-order solutions. This reduces NFEs by up to 5x while boosting quality (e.g., FID drops 53% on DIODE at 20 NFEs vs. 2nd-order baseline). Experiments on inpainting, stylization, and semantics-to-image tasks across resolutions up to 256x256 show DBMSolver sets new SOTA efficiency-quality tradeoffs, enabling real-world applicability. Our code is publicly available at https://github.com/snumprlab/dbmsolver.

Related papers

• Distilling Parallel Gradients for Fast ODE Solvers of Diffusion Models [53.087070073434845]
  Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature.<n>Existing solver-based acceleration methods often face image quality degradation under a low-latency budget.<n>We propose the Ensemble Parallel Direction solver (dubbed as ours), a novel ODE solver that mitigates truncation errors by incorporating multiple parallel gradient evaluations in each ODE step.
  arXiv  Detail & Related papers  (2025-07-20T03:08:06Z)
• Inverse Bridge Matching Distillation [69.479483488685]
  Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation.<n>We propose a novel distillation technique based on the inverse bridge matching formulation and derive the tractable objective to solve it in practice.<n>We evaluate our approach for both conditional and unconditional types of bridge matching on a wide set of setups, including super-resolution, JPEG restoration, sketch-to-image, and other tasks.
  arXiv  Detail & Related papers  (2025-02-03T13:56:03Z)
• Enhancing and Accelerating Diffusion-Based Inverse Problem Solving through Measurements Optimization [66.17291150498276]
  We introduce textbfMeasurements textbfOptimization (MO), a more efficient plug-and-play module for integrating measurement information at each step of the inverse problem-solving process.<n>By using MO, we establish state-of-the-art (SOTA) performance across multiple tasks, with key advantages.
  arXiv  Detail & Related papers  (2024-12-05T07:44:18Z)
• Consistency Diffusion Bridge Models [25.213664260896103]
  Diffusion bridge models (DDBMs) build processes between fixed data endpoints based on a reference diffusion process. DDBMs' sampling process typically requires hundreds of network evaluations to achieve decent performance. We propose two paradigms: consistency bridge distillation and consistency bridge training, which is flexible to apply on DDBMs with broad design choices.
  arXiv  Detail & Related papers  (2024-10-30T02:04:23Z)
• Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step [64.53013367995325]
  We introduce SiDA (SiD with Adversarial Loss), which improves generation quality and distillation efficiency.<n>SiDA incorporates real images and adversarial loss, allowing it to distinguish between real images and those generated by SiD.<n>SiDA converges significantly faster than its predecessor when distilled from scratch.
  arXiv  Detail & Related papers  (2024-10-19T00:33:51Z)
• Improved Distribution Matching Distillation for Fast Image Synthesis [54.72356560597428]
  We introduce DMD2, a set of techniques that lift this limitation and improve DMD training. First, we eliminate the regression loss and the need for expensive dataset construction. Second, we integrate a GAN loss into the distillation procedure, discriminating between generated samples and real images.
  arXiv  Detail & Related papers  (2024-05-23T17:59:49Z)
• You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs [13.133574069588896]
  YOSO is a novel generative model designed for rapid, scalable, and high-fidelity one-step image synthesis with high training stability and mode coverage.<n>We show that our method can serve as a one-step generation model training from scratch with competitive performance.<n>In particular, we show that the YOSO-PixArt-$alpha$ can generate images in one step trained on 512 resolution, with the capability of adapting to 1024 resolution without extra explicit training, requiring only 10 A800 days for fine-tuning.
  arXiv  Detail & Related papers  (2024-03-19T17:34:27Z)
• SpeedUpNet: A Plug-and-Play Adapter Network for Accelerating Text-to-Image Diffusion Models [4.232258232565518]
  Text-to-image diffusion models (SD) exhibit significant advancements while requiring extensive computational resources. LCM-LoRA, trainable once for diverse models, offers universality but rarely considers ensuring the consistency of generated content before and after acceleration. This paper proposes SpeedUpNet (SUN), an innovative acceleration module, to address the challenges of universality and consistency.
  arXiv  Detail & Related papers  (2023-12-13T09:42:04Z)
• ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models [59.90959789767886]
  We show that optimizing consistency training loss minimizes the Wasserstein distance between target and generated distributions. By incorporating a discriminator into the consistency training framework, our method achieves improved FID scores on CIFAR10 and ImageNet 64$times$64 and LSUN Cat 256$times$256 datasets.
  arXiv  Detail & Related papers  (2023-11-23T16:49:06Z)
• I$^2$SB: Image-to-Image Schr\"odinger Bridge [87.43524087956457]
  Image-to-Image Schr"odinger Bridge (I$2$SB) is a new class of conditional diffusion models. I$2$SB directly learns the nonlinear diffusion processes between two given distributions. We show that I$2$SB surpasses standard conditional diffusion models with more interpretable generative processes.
  arXiv  Detail & Related papers  (2023-02-12T08:35:39Z)

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.