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

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 \textbf{DBMSolver}, a training-free sampler that exploits the semi-linear structure of DBM's underlying SDE and ODE via exponential integrators, yielding exact $1^\text{st}$- and $2^\text{nd}$-order solutions. This reduces NFEs by up to $5\times$ while boosting quality (e.g., FID drops $53\%$ on DIODE at 20 NFEs vs. $2^\text{nd}$-order baseline). Experiments on inpainting, stylization, and semantics-to-image tasks across resolutions up to 256$\times$256 show DBMSolver sets new SOTA efficiency-quality tradeoffs, enabling real-world applicability.