$γ$-Bridge: A Look-Parametric Diffusion Bridge

2026-07-21

AI Summary

This work addresses key limitations in existing synthetic aperture radar (SAR) image despeckling methods—namely, their reliance on signal-to-noise ratio schedules decoupled from physical parameters, poor cross-scenario generalization, and the absence of real clean training data—by introducing γ-Bridge, a diffusion bridge model parameterized by the observed number of looks $L$. The approach constructs a forward process through precise modeling of the Gamma marginal distribution and enables stable multi-step inference via a closed-form Gamma–Lévy reverse posterior. By directly parameterizing the diffusion process with $L$ and integrating an observation-conditioning mechanism with a two-step consistency loss, γ-Bridge requires training only on natural images with $L=1$ yet achieves zero-shot generalization across six diverse spaceborne and airborne SAR datasets. It attains state-of-the-art performance on synthetic benchmarks while offering physically interpretable input–output control.

Abstract

Multiplicative Gamma noise is a signal-dependent degradation in coherent imaging; synthetic aperture radar (SAR) despeckling is its most prominent real-world instance. Existing diffusion denoisers parameterize their forward process by abstract signal-to-noise schedules rather than by the physical look number $L$, so different deployment scenarios typically require separately trained models, and transfer from synthetic Gamma training to real SAR remains challenging without clean ground truth. We introduce $γ$-Bridge, a look-parametric bridge whose schedule $L(t)$ connects the noisy observation at $L_{obs}$ to the clean limit through exact multiplicative Gamma marginals. Its closed-form Gamma--Lévy reverse posterior admits both stochastic and deterministic processes, while observation conditioning and a two-step consistency loss stabilize multi-step inference in the low-SNR single-look regime. Because bridge time directly represents $L$, one conditioned network can smart-start from any admissible input look and stop at a target look number. These two orthogonal controls enable zero-shot restoration over the full admissible grid after training only at $L_{obs} = 1$ on natural images with synthetic Gamma corruption. Combined with a homogeneous-patch look estimator, $γ$-Bridge processes data from six spaceborne and airborne SAR sensors without sensor-specific fine-tuning, achieving leading results on standard synthetic benchmarks while providing physically interpretable input and output controls absent from prior denoisers. Codes are released \href{https://github.com/Teriri1999/GammaBridge}{here}.

Problem

• multiplicative Gamma noise
• SAR despeckling
• look number
• diffusion denoising
• signal-dependent degradation

Innovation

• look-parametric diffusion
• multiplicative Gamma noise
• diffusion bridge
• SAR despeckling
• zero-shot restoration