Toward a Training-Free Plug-and-play Refinement Framework for Infrared and Visible Image Registration and Fusion

🔍 Overview

This repository contains the official resources for the paper: “Toward a Training-Free Plug-and-play Refinement Framework for Infrared and Visible Image Registration and Fusion”. We propose TRACE, a Training-free Reinforcement-based Alignment method for Cross-modality Enhancement, which incorparates Evaluator, a rewarding network, into an evaluation-driven Reinforcement Learning(RL) framework, enabling efficient and plug-and-play refinement of any existing registration approach.

📝 TODO List

 □ Environment Setup. Provide full conda or pip environment configuration (requirements.txt / environment.yml).

 □ Release Rewarding Model Code (2025/12/25)
 
 □ Release Trace Code
 
 □ Release Testing Samples

 □ Release Pretrained Weights

📁 Project Structure (to appear)