{"slug": "gamma-bridge-a-look-parametric-diffusion-bridge", "title": "$\\gamma$-Bridge: A Look-Parametric Diffusion Bridge", "summary": "Researchers introduce γ-Bridge, a look-parametric diffusion bridge for SAR despeckling that uses a schedule L(t) connecting noisy observations at L_obs to the clean limit via exact multiplicative Gamma marginals. The method achieves zero-shot restoration over the full admissible grid after training only at L_obs=1 on natural images with synthetic Gamma corruption, and processes data from six spaceborne and airborne SAR sensors without sensor-specific fine-tuning.", "body_md": "arXiv:2607.22719v1 Announce Type: new\nAbstract: 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 $\\gamma$-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--L\\'evy 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, $\\gamma$-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}.", "url": "https://wpnews.pro/news/gamma-bridge-a-look-parametric-diffusion-bridge", "canonical_source": "https://arxiv.org/abs/2607.22719", "published_at": "2026-07-28 04:00:00+00:00", "updated_at": "2026-07-28 04:08:44.593066+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "computer-vision"], "entities": ["γ-Bridge", "arXiv", "SAR"], "alternates": {"html": "https://wpnews.pro/news/gamma-bridge-a-look-parametric-diffusion-bridge", "markdown": "https://wpnews.pro/news/gamma-bridge-a-look-parametric-diffusion-bridge.md", "text": "https://wpnews.pro/news/gamma-bridge-a-look-parametric-diffusion-bridge.txt", "jsonld": "https://wpnews.pro/news/gamma-bridge-a-look-parametric-diffusion-bridge.jsonld"}}