Annealed Langevin Posterior Sampling (ALPS): A Rapid Algorithm for Image Restoration with Multiscale Energy Models

Jyothi Rikhab Chand; Mathews Jacob

doi:10.48550/arxiv.2601.02594

Back

Annealed Langevin Posterior Sampling (ALPS): A Rapid Algorithm for Image Restoration with Multiscale Energy Models

Preprint

Open access

Annealed Langevin Posterior Sampling (ALPS): A Rapid Algorithm for Image Restoration with Multiscale Energy Models

Jyothi Rikhab Chand and Mathews Jacob

ArXiv.org

Cornell University

01/05/2026

DOI: 10.48550/arxiv.2601.02594

Files and links (1)

url

https://doi.org/10.48550/arxiv.2601.02594View

Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

Solving inverse problems in imaging requires models that support efficient inference, uncertainty quantification, and principled probabilistic reasoning. Energy-Based Models (EBMs), with their interpretable energy landscapes and compositional structure, are well-suited for this task but have historically suffered from high computational costs and training instability. To overcome the historical shortcomings of EBMs, we introduce a fast distillation strategy to transfer the strengths of pre-trained diffusion models into multi-scale EBMs. These distilled EBMs enable efficient sampling and preserve the interpretability and compositionality inherent to potential-based frameworks. Leveraging EBM compositionality, we propose Annealed Langevin Posterior Sampling (ALPS) algorithm for Maximum-A-Posteriori (MAP), Minimum Mean Square Error (MMSE), and uncertainty estimates for inverse problems in imaging. Unlike diffusion models that use complex guidance strategies for latent variables, we perform annealing on static posterior distributions that are well-defined and composable. Experiments on image inpainting and MRI reconstruction demonstrate that our method matches or surpasses diffusion-based baselines in both accuracy and efficiency, while also supporting MAP recovery. Overall, our framework offers a scalable and principled solution for inverse problems in imaging, with potential for practical deployment in scientific and clinical settings. ALPS code is available at the GitHub repository https://github.com/JyoChand/ALPSALPS.

Computer Science - Artificial Intelligence

Computer Science - Computer Vision and Pattern Recognition

Details

Title: Subtitle: Annealed Langevin Posterior Sampling (ALPS): A Rapid Algorithm for Image Restoration with Multiscale Energy Models
Creators: Jyothi Rikhab Chand
Mathews Jacob
Resource Type: Preprint
Publication Details: ArXiv.org
DOI: 10.48550/arxiv.2601.02594
ISSN: 2331-8422
Publisher: Cornell University; Ithaca, New York
Number of pages: 20 pages
Language: English
Date posted: 01/05/2026
Academic Unit: Electrical and Computer Engineering
Record Identifier: 9985121625802771

Metrics

1 Record Views