Seeing Through the PRISM: Compound & Controllable Restoration of Scientific Images

TL;DR

PRISM is a novel diffusion-based framework that enables precise, controllable, and high-fidelity restoration of complex, compound degradations in scientific images, improving accuracy and interpretability across various scientific domains.

Contribution

It introduces a prompted conditional diffusion model with a contrastive disentanglement objective for simultaneous, selective removal of multiple image degradations.

Findings

Outperforms state-of-the-art methods on complex degradations.

Enables zero-shot removal of unseen degradation mixtures.

Improves downstream scientific analysis accuracy.

Abstract

Scientific and environmental imagery often suffer from complex mixtures of noise related to the sensor and the environment. Existing restoration methods typically remove one degradation at a time, leading to cascading artifacts, overcorrection, or loss of meaningful signal. In scientific applications, restoration must be able to simultaneously handle compound degradations while allowing experts to selectively remove subsets of distortions without erasing important features. To address these challenges, we present PRISM (Precision Restoration with Interpretable Separation of Mixtures). PRISM is a prompted conditional diffusion framework which combines compound-aware supervision over mixed degradations with a weighted contrastive disentanglement objective that aligns primitives and their mixtures in the latent space. This compositional geometry enables high-fidelity joint removal of overlapping distortions while also allowing flexible, targeted fixes through natural language prompts. Across microscopy, wildlife monitoring, remote sensing, and urban weather datasets, PRISM outperforms state-of-the-art baselines on complex compound degradations, including zero-shot mixtures not seen during training. Importantly, we show that selective restoration significantly improves downstream scientific accuracy in several domains over standard "black-box" restoration. These results establish PRISM as a generalizable and controllable framework for high-fidelity restoration in domains where scientific utility is a priority.