AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

PIU-CR: Physics-Informed Deep Unfolding Network with SAR-Optical Image Fusion for Cloud Removal

Gengque Fan, Han Xu, Junxi Li, Hao Zhang, Guangcan Liu, Jiayi Ma

NeurIPS 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion

Read the paperCheck your idea against 137,217 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 PIU-CR, a physics-informed deep unfolding network that fuses SAR and optical images for cloud removal, aiming for interpretable cross-modal interactions grounded in a more faithful physical model.

Problem

Multi-modal cloud removal from cloud-degraded optical imagery using SAR; existing methods are black-box and physical priors used in networks are oversimplified, limiting interpretability of cross-modal interactions.

Approach

Unfolds an optimization built on a physics-informed formulation of the optical-SAR imaging/cloud degradation process into a deep network, so each stage corresponds to an iterative solver step with learned cross-modal fusion, rather than oversimplified physical priors inside a black-box network.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy