Inconsistency-aware Multimodal Schr\"odinger Bridge for Deepfake Localization

Researchers have developed IaMSB, an inconsistency-aware multimodal Schrödinger Bridge framework that improves deepfake localization by jointly estimating cross-modal consistency and performing interval-level temporal evidence detection. The method addresses the challenge of symmetric fusion under single-sided or asynchronous forgeries, which propagates cross-modal noise and degrades precision. Across benchmarks, IaMSB raises strict-IoU boundary precision by 3% to 10%, particularly improving high-precision localization for single-sided forgeries.

arXiv:2605.23113v1 Announce Type: new Abstract: Audio-visual deepfake localization demands interval-level outputs that serve as temporal evidence. Despite recent progress, symmetric fusion under single-sided or asynchronous forgeries propagates cross-modal noise, degrading high-precision localization. We present IaMSB, an inconsistency-aware multimodal Schr\"odinger Bridge SB that jointly estimates cross-modal consistency and performs interval-level localization. Unlike diffusion models, SB minimizes path-distribution discrepancy and yields consistency scores without explicit noise injection or denoising. With the Schr\"odinger Bridge SB , IaMSB unifies consistency estimation, cross-modal information selection, and bridge-step scheduling in one framework. Specifically, a lightweight coarse bridge first proposes candidate intervals and estimates cross-modal consistency; these statistics select cross-modal witness signals and allocate bridge steps asymmetrically across modalities. A refinement bridge then performs step-tuned fusion and outputs refined, time-aligned intervals. IaMSB anticipates single-sided and asynchronous forgeries and, using bottlenecked cross-modal interaction with step allocation, suppresses noise transfer, avoids unnecessary iterations. Across benchmarks, IaMSB stabilizes strict-IoU boundary precision, raising AP@0.95 by 3%~10%, and yields improved high-precision localization, particularly for single-sided forgeries.