CVNov 23, 2025

Robust Posterior Diffusion-based Sampling via Adaptive Guidance Scale

arXiv:2511.18471v1
Originality Incremental advance
AI Analysis

This work addresses a key bottleneck in applying diffusion models to inverse problems in imaging, offering a robust and hyperparameter-free method that enhances reconstruction quality without task-specific tuning, though it is incremental as it builds on existing diffusion-based approaches.

The paper tackled the challenge of balancing prior and data fidelity in diffusion models for inverse problems by proposing an adaptive likelihood step-size strategy, resulting in improved reconstruction quality across imaging tasks like super-resolution and deblurring on datasets such as CelebA-HQ and ImageNet-256, with consistent gains in perceptual quality and minimal distortion loss.

Diffusion models have recently emerged as powerful generative priors for solving inverse problems, achieving state-of-the-art results across various imaging tasks. A central challenge in this setting lies in balancing the contribution of the prior with the data fidelity term: overly aggressive likelihood updates may introduce artifacts, while conservative updates can slow convergence or yield suboptimal reconstructions. In this work, we propose an adaptive likelihood step-size strategy to guide the diffusion process for inverse-problem formulations. Specifically, we develop an observation-dependent weighting scheme based on the agreement between two different approximations of the intractable intermediate likelihood gradients, that adapts naturally to the diffusion schedule, time re-spacing, and injected stochasticity. The resulting approach, Adaptive Posterior diffusion Sampling (AdaPS), is hyperparameter-free and improves reconstruction quality across diverse imaging tasks - including super-resolution, Gaussian deblurring, and motion deblurring - on CelebA-HQ and ImageNet-256 validation sets. AdaPS consistently surpasses existing diffusion-based baselines in perceptual quality with minimal or no loss in distortion, without any task-specific tuning. Extensive ablation studies further demonstrate its robustness to the number of diffusion steps, observation noise levels, and varying stochasticity.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes