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

2026-03-14

AI Summary

This work proposes PRISM, a novel framework for scientific and environmental image restoration that addresses the challenge of mixed noise degradation. Unlike conventional sequential denoising approaches—which often introduce artifacts, over-correction, or critical signal loss and lack selectivity—PRISM jointly models and interprets composite degradations within a unified architecture. It leverages a prompt-driven conditional diffusion model, composite-aware supervision, weighted contrastive learning, and latent-space geometric alignment to enable high-fidelity joint restoration and natural language-guided selective editing. The method supports zero-shot generalization to unseen noise combinations and demonstrates superior performance across diverse domains, including microscopy, wildlife monitoring, remote sensing, and urban meteorological data, while significantly enhancing the accuracy of downstream scientific analyses.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multimodal Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

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.

Problem

• compound degradation
• controllable restoration
• scientific image restoration
• selective denoising
• multi-distortion removal

Innovation

• compound degradation
• prompted conditional diffusion
• contrastive disentanglement
• selective restoration
• scientific image restoration