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

• URL: http://arxiv.org/abs/2607.22719v1
• Date: Tue, 21 Jul 2026 18:45:58 GMT
• Title: $γ$-Bridge: A Look-Parametric Diffusion Bridge
• Abstract summary: Multiplicative Gamma noise is a signal-dependent degradation in coherent imaging.<n>We introduce $$-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.
• Score: 1.6583003147024213
• License: http://creativecommons.org/publicdomain/zero/1.0/
• 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}.

Related papers

• LF-GICP: Parameter-Free Degeneracy-Aware LiDAR Odometry via a Voxel-Normal Localizability Field [0.0]
  Scan-to-map LiDAR odometry drifts unbounded along the unobservable axes of geometrically degenerate environments.<n>We show that in voxelized GICP the Gauss--Newton (GN) Hessian masks translational degeneracy, because covariance regularization keeps the translation block artificially well-conditioned.<n>We bypass this with a regularization-free voxel-normal localizability field and two of its statistics.
  arXiv  Detail & Related papers  (2026-08-20T00:36:24Z)
• Robust Average-Reward Markov Decision Processes: Minimax-Optimal Learning via Plug-in Reductions [51.50375419691955]
  Distributionally robust Markov decision processes provide a principled framework for sequential decision making under model uncertainty.<n>We study how many samples are necessary and sufficient to learn an $varepsilon$-optimal robust policy under the average-reward criterion.
  arXiv  Detail & Related papers  (2026-08-06T19:49:48Z)
• Flow Map Denoisers: Traversing the Distortion-Perception Plane for Inverse Problems [48.501415601682815]
  Image restoration faces a fundamental tradeoff: methods that minimize error produce blurry reconstructions, while those that maximize perceptual quality yield sharp but less faithful images.<n>We show that flow map models implicitly define a one- parameter family of denoisers that continuously spans the distortion perception frontier.<n>Within a Plug-and-Play solver, the same mechanism extends to general inverse problems, where it controls a tradeoff between perceptual alignment and data consistency.
  arXiv  Detail & Related papers  (2026-06-18T05:15:43Z)
• Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution [27.232771005158146]
  Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution.<n>We introduce $textbfSKILD$, a model that unifies generation and continuous super-resolution within a single unconditional framework.<n> Empirically, SKILD reaches FID $2.65$ and Inception Score $9.63$ on unconditional CIFAR-10, performs $2times$--$8times$ super-resolution on ImageNet from a single unconditional checkpoint.
  arXiv  Detail & Related papers  (2026-05-25T17:01:21Z)
• Zeno-Enhanced Probabilistic Error Cancellation with Quantum Error Detection Codes [2.6031571481535143]
  We exploit a complementarity between quantum error-detecting codes and probabilistic error cancellation.<n>We map physical noise to a weaker accepted logical channel, and then applying PEC only to the residual channel.<n>The resulting feedback-free QED+PEC scheme interleaves Clifford logical blocks, stabilizer measurements, post-selection, and probabilistic cancellation.
  arXiv  Detail & Related papers  (2026-05-12T14:06:27Z)
• Spectral Tempering for Embedding Compression in Dense Passage Retrieval [17.660889990235656]
  We show that the optimal scaling strength $$ is not a global constant.<n>We propose Spectral Tempering, a learning-free method that derives an adaptive $(k)$ directly from the corpus eigenspectrum.
  arXiv  Detail & Related papers  (2026-03-19T10:01:32Z)
• Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning [61.07540493350384]
  Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth and the teacher's own predictions.<n>We show that for any prediction risk, the optimally mixed student improves upon the ridge teacher for every regularization level.<n>We propose a consistent one-shot tuning method to estimate $star$ without grid search, sample splitting, or refitting.
  arXiv  Detail & Related papers  (2026-02-19T17:21:15Z)
• Hardware-Agnostic Modeling of Quantum Side-Channel Leakage via Conditional Dynamics and Learning from Full Correlation Data [0.0]
  We study a sequential side-channel model in which an adversarial probe qubit interacts with a target qubit during a hidden gate sequence.<n>Repeating the same hidden sequence for $N$ shots yields an empirical full-correlation record.<n>Experiments over broad coupling and noise grids show that strict sequence recovery concentrates near the predicted coupling band.
  arXiv  Detail & Related papers  (2026-02-17T19:33:23Z)
• Accelerated characterization of two-level systems in superconducting qubits via machine learning [74.02542457579791]
  We introduce a data-driven approach for extracting two-level system (TLS) parameters-frequency $omega_TLS$, coupling strength $g$, dissipation time $T_TLS, 1$, and the pure dephasing time $Tphi_TLS, 2$.<n>A custom convolutional neural network model(CNN) can simultaneously predict $omega_TLS$, $g$, $T_TLS, 1$ and $Tphi_TLS, 2$ from the spectroscopy data presented in the form of
  arXiv  Detail & Related papers  (2025-09-22T12:55:52Z)
• Multistep Inverse Is Not All You Need [87.62730694973696]
  In real-world control settings, the observation space is often unnecessarily high-dimensional and subject to time-correlated noise. It is therefore desirable to learn an encoder to map the observation space to a simpler space of control-relevant variables. We propose a new algorithm, ACDF, which combines multistep-inverse prediction with a latent forward model.
  arXiv  Detail & Related papers  (2024-03-18T16:36:01Z)
• On Leaky-Integrate-and Fire as Spike-Train-Quantization Operator on Dirac-Superimposed Continuous-Time Signals [0.5439020425819]
  Leaky-integrate-and-fire (LIF) is studied as a non-linear operator that maps an integrable signal $f$ to a sequence $eta_f$ of discrete events, the spikes. We prove the quantization formula $|eta_f - f|_A, alpha$ with leaky parameter $alpha$ under the general condition of local integrability.
  arXiv  Detail & Related papers  (2024-02-10T17:07:19Z)
• Approximate Autonomous Quantum Error Correction with Reinforcement Learning [4.015029887580199]
  Autonomous quantum error correction (AQEC) protects logical qubits by engineered dissipation. Bosonic code spaces, where single-photon loss represents the dominant source of error, are promising candidates for AQEC. We propose a bosonic code for approximate AQEC by relaxing the Knill-Laflamme conditions.
  arXiv  Detail & Related papers  (2022-12-22T12:42:52Z)
• Neural Inference of Gaussian Processes for Time Series Data of Quasars [72.79083473275742]
  We introduce a new model that enables it to describe quasar spectra completely. We also introduce a new method of inference of Gaussian process parameters, which we call $textitNeural Inference$. The combination of both the CDRW model and Neural Inference significantly outperforms the baseline DRW and MLE.
  arXiv  Detail & Related papers  (2022-11-17T13:01:26Z)
• The Generalized Lasso with Nonlinear Observations and Generative Priors [63.541900026673055]
  We make the assumption of sub-Gaussian measurements, which is satisfied by a wide range of measurement models. We show that our result can be extended to the uniform recovery guarantee under the assumption of a so-called local embedding property.
  arXiv  Detail & Related papers  (2020-06-22T16:43:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.