Direct Conditional Transition Sampling for Diffusion Inverse Problems

• URL: http://arxiv.org/abs/2609.14596v1
• Date: Sun, 13 Sep 2026 15:24:33 GMT
• Title: Direct Conditional Transition Sampling for Diffusion Inverse Problems
• Abstract summary: Training-free diffusion inverse solvers typically choose between local measurement guidance and costly clean-space posterior updates.<n>We propose Direct Transition Sampling (DCTS), a direct Conditional-flow approximation to the same ideal refresh target.<n>DCTS achieves competitive reconstruction quality with up to $16.8times$ speedups over competing methods.
• Score: 16.85590645425029
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training-free diffusion inverse solvers typically choose between local measurement guidance and costly clean-space posterior updates. Independent posterior refresh can improve global correction by sampling a clean conditional and re-noising it, but its practical realization requires probability-flow ODE integration and clean-space Markov chain Monte Carlo (MCMC). We propose Direct Conditional Transition Sampling (DCTS), a direct stochastic-flow approximation to the same ideal refresh target. Rather than explicitly drawing a clean sample, DCTS estimates the measurement-conditioned clean mean along a short inner path and transports Gaussian source noise directly to the next noisy state. A denoiser-compatible sufficient statistic and a covariance-scaled operator update enable this conditional-mean estimation. Experiments on four inverse problems demonstrate that DCTS achieves competitive reconstruction quality with up to $16.8\times$ speedups over competing methods.

Related papers

• Fast and Faithful: Principled Conditional Flow Matching for Inverse Problems [8.966524060251965]
  Flow matching approaches to imaging inverse problems commonly incorporate measurements in two ways.<n>We propose a principled parametrization of the measurement-conditional velocity field to solve inverse problems.<n>Our method achieves state-of-the-art PSNR with $50times$ fewer evaluations function than the strongest flow baseline.
  arXiv  Detail & Related papers  (2026-09-11T15:12:11Z)
• MoRF-AST: Calibrated Probabilistic Virtual Sensing for Structural Monitoring under Changing Operating Conditions [10.208843473977094]
  This study proposes Modal Residual Flow Matching with Context-Conditioned Affine Spread Transport (MoRF-AST) for calibrated structural virtual sensing.<n>MoRF achieves a posterior-mean normalized root-mean-square error (NRMSE) of 7.20%, compared with 16.1% and 17.9% for two direct conditional flows.
  arXiv  Detail & Related papers  (2026-08-25T13:16:59Z)
• Stochastic Optimal Control Sampling for Diffusion Inverse Problems [35.41392757423596]
  We introduce Optimal Control Sampling (SOCS), which models the denoising process as a dynamical system and injects control signals via SOC.<n>Our method is compatible with a variety of linear differential equation reconstructions with improved visual fidelity and stronger quantitative performance.
  arXiv  Detail & Related papers  (2026-06-27T07:34:52Z)
• On the Error-Correcting Effects of Stochasticity in Discrete Diffusion [0.0]
  Discrete diffusion models achieve strong performance in text and image generation, but their inference remains slow and must inherently balance sampling and sample quality.<n>We show that highly deterministic transitions converge rapidly but suffer from error accumulation, while more transitions converge more slowly yet can achieve higher final sample quality.<n>Motivated by this analysis, we propose emphDiscrete Churn and Restart Sampling (DCRS), a novel inference algorithm that injects controlledity by alternating between forward and reverse diffusion processes.
  arXiv  Detail & Related papers  (2026-05-26T05:58:46Z)
• Tempered Guided Diffusion [1.7778609937758325]
  We propose a sequential Monte Carlo framework for training-free conditional sampling with diffusion priors.<n>TGD targets tempered posterior distributions over the clean signal, using noisy diffusion states only as auxiliary variables.<n>For expensive reconstruction tasks, TGD retains early particle exploration but prunes to a single high-likelihood trajectory partway through sampling.
  arXiv  Detail & Related papers  (2026-05-05T13:00:15Z)
• Diffusion Controller: Framework, Algorithms and Parameterization [54.82539154511621]
  We present a unified control-theoretic view that casts reverse diffusion sampling as state-only control within (generalized) linearly-solvable Markov Decision Processes.<n>Under this framework, control acts by reweighting the pretrained reverse-time transition kernels, balancing terminal objectives against an $f$-divergence cost.<n>Experiments on Stable Diffusion v1.4 show consistent gains in preference-alignment win rates and improved quality-efficiency trade-offs.
  arXiv  Detail & Related papers  (2026-03-07T01:49:59Z)
• Distributional Diffusion Models with Scoring Rules [83.38210785728994]
  Diffusion models generate high-quality synthetic data.<n> generating high-quality outputs requires many discretization steps.<n>We propose to accomplish sample generation by learning the posterior em distribution of clean data samples.
  arXiv  Detail & Related papers  (2025-02-04T16:59:03Z)
• DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation [68.55191764622525]
  Diffusion models (DPMs) have shown remarkable performance in visual synthesis but are computationally expensive due to the need for multiple evaluations during the sampling. Recent predictor synthesis-or diffusion samplers have significantly reduced the required number of evaluations, but inherently suffer from a misalignment issue. We introduce a new fast DPM sampler called DC-CPRr, which leverages dynamic compensation to mitigate the misalignment.
  arXiv  Detail & Related papers  (2024-09-05T17:59:46Z)
• Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion [56.38386580040991]
  Consistency Trajectory Model (CTM) is a generalization of Consistency Models (CM) CTM enables the efficient combination of adversarial training and denoising score matching loss to enhance performance. Unlike CM, CTM's access to the score function can streamline the adoption of established controllable/conditional generation methods.
  arXiv  Detail & Related papers  (2023-10-01T05:07:17Z)
• Latent Class-Conditional Noise Model [54.56899309997246]
  We introduce a Latent Class-Conditional Noise model (LCCN) to parameterize the noise transition under a Bayesian framework. We then deduce a dynamic label regression method for LCCN, whose Gibbs sampler allows us efficiently infer the latent true labels. Our approach safeguards the stable update of the noise transition, which avoids previous arbitrarily tuning from a mini-batch of samples.
  arXiv  Detail & Related papers  (2023-02-19T15:24:37Z)
• On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging [96.13485146617322]
  We present an analysis of the ExtraGradient (SEG) method with constant step size, and present variations of the method that yield favorable convergence. We prove that when augmented with averaging, SEG provably converges to the Nash equilibrium, and such a rate is provably accelerated by incorporating a scheduled restarting procedure.
  arXiv  Detail & Related papers  (2021-06-30T17:51:36Z)

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.