Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges

arXiv:2605.02973v3 Announce Type: replace-cross
Abstract: Modality translation is inherently under-constrained, as multiple cross-modal mappings may yield the same marginals. Recent work has shown that diffusion bridges are effective for this task. However, most existing approaches rely on fully paired datasets, thereby imposing a single data-driven constraint. We propose a diffusion-bridge framework that characterizes the space of admissible solutions and restricts it via alignment constraints, treating paired supervision as an optional heuristic rather than a prerequisite. We validate our method on synthetic and real modality translation benchmarks across unpaired, semi-paired, and paired regimes, showing consistent performance across supervision levels. Notably, textbfit achieves near fully-paired quality with a substantial relaxation in pairing requirements, and remaining applicable in the unpaired regime. These results highlight diffusion bridges as a flexible foundation for modality translation beyond fully paired data.