Skip to main content
Search

# Diffusion Posterior Sampling

4 related articles

Subscribe to updates
  1. arXiv

    UAV SAR drops the straight-and-level assumption: a diffusion prior plus motion compensation holds 21.3 dB at half physical resolution

    A UAV ISAC synthetic aperture radar imager casts imaging as an exact linear inverse problem, using a pretrained diffusion model as prior and the echoes as likelihood guidance to reconstruct super-resolution images under arbitrary known trajectories and unknown position errors.

  2. arXiv

    Subsurface fracture networks skip fracture-by-fracture sampling: a latent diffusion model generates native 3D voxel fields and honors 84.2% of sparse well voxels

    Subsurface fracture networks were previously sampled fracture by fracture from prescribed statistics, which made sparse well observations hard to enforce. Here 2D and 3D networks are represented as binary occupancy fields, compressed by a variational autoencoder into a compact latent space, and learned by a diffusion model, with well observations injected through a learned conditioning encoder, classifier-free guidance, and diffusion posterior sampling. The 2D conditional model satisfies 99.6% of prescribed well observations, while the native 3D volumetric field satisfies 84.2% of observed well voxels while keeping fracture volume fraction close to the reference ensemble.

  3. arXiv

    Spatial prediction without retraining per data model: one process model handles counts, censoring and areal aggregates

    Spatial prediction targets the conditional distribution of a latent spatial field given observations, which is rarely available in closed form and is hard to sample. Guided diffusion separates the two: an unconditional diffusion model is trained on the process model alone, and a differentiable likelihood gradient is added during reverse diffusion at prediction time, so one trained process model serves many data models. Across Gaussian processes, a Ginzburg–Landau amplitude field and a methane-flux inversion over the UK and Ireland, the predictive distributions match exact or MCMC results and scale linearly with the latent dimension at higher resolutions.

  4. arXiv

    SIMCA calibrates guidance weights offline by least squares, letting diffusion and flow-matching posterior sampling match or beat prior methods within 50 steps

    The authors introduce SIMCA: observing that the conditional denoising score-matching objective for diffusion models and the conditional flow-matching objective for flow-matching models are least-squares objectives in the guidance weights at each time step, they reduce guidance-weight tuning in training-free posterior sampling to a two-dimensional linear least-squares problem solved offline by a greedy simulation-based calibration that needs only a single minibatch of sampling trajectories and no retraining; across several inverse problems on FFHQ, ImageNet, CelebA and AFHQ-Cat, the method matches or surpasses state-of-the-art training-free methods and lets diffusion samplers cut steps from 1000 to 50 without significant degradation in reconstruction quality.

You’re all caught up