Research map / Image generation / Image restoration

Zero-Shot Burst Restoration via Diffusion MAP Inference with Poisson-Gaussian Noise Likelihood

NeurIPS 2026 · Image generation › Image restoration · approach: Inverse imaging with learned priors

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a training-free, zero-shot burst image restoration method that uses diffusion MAP inference with a Poisson-Gaussian noise likelihood.

Problem

Burst image restoration needs high-quality images from low-quality frame sequences; supervised methods require paired data and generalize poorly across camera sensors and noise levels.

Approach

Zero-shot diffusion-based restoration framed as MAP inference using a Poisson-Gaussian noise likelihood for burst frames, requiring no training. Details beyond the abstract are not stated.

Closest papers by meaning

• Diffusion Priors for Variational Likelihood Estimation and Image Denoising (NeurIPS 2024 · similarity 0.88)
• Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models (NeurIPS 2026 · similarity 0.87)
• SinSR: Diffusion-Based Image Super-Resolution in a Single Step (CVPR 2024 · similarity 0.87)
• QMambaBSR: Burst Image Super-Resolution with Query State Space Model (CVPR 2025 · similarity 0.87)
• Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual (CVPR 2025 · similarity 0.87)
• BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution (AAAI 2025 · similarity 0.86)