Jia-Yi Ma

IterRF: Iterative and Interpretable Mutual Enhancement for Joint Multi-Modal Image Registration and Fusion

SeeRF: Learning to See Beyond Fields of View via Generative Image Registration and Fusion

A generative registration-fusion framework that overcomes the limitations imposed by shared fields of view and enables effective completion and natural fusion of non-overlapping field-of-view regions is proposed.

AD-SRF: Attack-Defense Semantic Reinforcement for Multi-Modal Image Fusion

Existing image fusion methods struggle to balance visual quality and semantic attributes due to the inherent conflict between their optimization objectives. To address this challenge, we propose an attack-defense semantic reinforcement framework for multi-modal image fusion, termed AD-SRF. By decoupling the optimizatio...

Diff-RF: Mutually Reinforced Image Registration and Fusion via Degradation-Aware Learning

Diff-RF explores the intrinsic coupling between registration-fusion and information restoration in the degradation conditions, enabling high-quality fusion of unregistered images under complex degradation conditions.

Win-Win Fusion: Multi-Modal Image Fusion with Visual-Semantic Collaboration

Existing multi-modal image fusion (MMIF) methods generally face an optimization gap between the visual and semantic domains, limiting the enhancement of perception capabilities. To overcome this long-standing barrier, this work proposes W2F, a new visual-semantic mutual reinforcing paradigm for MMIF. First, we reinforc...

SpeciFuse: Learning Degradation-Type Specificity for Robust Infrared and Visible Image Fusion Under Composite Degradations

SpeciFuse, an infrared-visible image fusion network that learns degradation-specific representations that effectively addresses the conflicts arising from multiple degradations, thereby achieving robust fusion performance that generalizes to diverse composite degradation scenarios.

Towards Heterogeneous-Degradation-Robust Image Fusion with Controllable Generative Modulation.

DuS-DiFuse is proposed, a robust dual-stream latent diffusion framework composed of a diffusion fusion unit and a generative modulation unit that achieves leading fusion performance, exhibits strong robustness to heterogeneous degradations, generalizes well across fusion tasks, and supports effective controllable gener...

GText-IF: Leveraging Text-Driven Semantics for Degradation-Aware Image Fusion.

An innovative degradation-aware image fusion framework via leveraging text-driven semantics, termed GText-IF, which can perform effective degradation-aware fusion in real degraded image scenarios, exhibiting remarkable advancement, robustness, and practicality.