← Back to all news
arXiv Machine Learning By Merve Kocabas, Benjamin A. Burns, Andreas Geiger, Kent Gauen, Sara Fridovich-Keil

Beyond Best-of-$k$: Prior-Consistent DAPS for Ambiguous Nonlinear Inverse Problems

Read the original on arXiv Machine Learning →

The paper introduces Prior-Consistent DAPS (PC‑DAPS), a variant of Decoupled Annealing Posterior Sampling designed to handle ambiguous nonlinear inverse problems where multiple measurement‑consistent solutions exist. PC‑DAPS maintains several candidate solutions in a single sampling run and prunes or replaces weaker candidates based on prior consistency as annealing noise decreases, without requiring ground‑truth access. This approach reduces prior‑inconsistent samples and improves sample quality for nonlinear inverse problems while preserving quality and diversity for linear ones.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computer Vision
Oct 2

Principled Design of Diffusion-based Optimizers for Inverse Problems

Score‑based diffusion models excel at inverse problems but suffer from slow inference and task‑specific hyperparameter tuning. This paper introduces principled reparameterizations that create invariances, enabling the reuse of the same hyperparameters across different tasks. Building on the RED‑diff framework, the authors present OptDiff, a streamlined pipeline that integrates convex optimization to accelerate inference, achieving notable speedups and higher image quality in reconstruction, deblurring, and super‑resolution experiments.

By Julio Oscanoa, Irmak Sivgin, Cagan Alkan, Daniel Ennis, John Pauly, Mert Pilanci, Shreyas Vasanawala
diffusionbenchmarks
More like this →
arXiv AI
Oct 5

Consecutive Posterior Fusion for Diffusive Recovery of Unobservable Image Structures

The paper introduces Consecutive Posterior Fusion Denoising Diffusion Null‑Space Models (CPF‑DDNM), an inference‑time method that fuses successive measurement‑aware estimates to better recover unobservable image structures in severely ill‑posed imaging inverse problems. CPF‑DDNM builds on DDNM’s range/null‑space decomposition, preserving measurement‑determined components while refining prior‑driven null‑space estimates. Experiments on sparse‑view CT, low‑dose CT, and medical image super‑resolution demonstrate consistent improvements over DDNM and competitive performance against other diffusion‑based inverse solvers.

By Elena Morotti, Davide Evangelista, Elena Loli Piccolomini
diffusion
More like this →