iconLogo
Published:2025/10/23 10:07:21

キラめき画像融合!ControlFusion で劣化に負けない最強画質✨

  1. 超要約: 劣化画像 (ノイズとか) を、言葉で命令してキレイにする技術!

  2. ギャル的キラキラポイント✨

    • ● 言葉で「もっと鮮明に!」とか指示できるから、超絶カンタン操作💖
    • ● 物理シミュレーションで、リアルな劣化にもバッチリ対応なんだって😳
    • ● セキュリティとか自動運転とか、色んな分野で活躍できるって、マジすごい🤩
  3. 詳細解説

    • 背景: 写真って、雨とかブレとかで劣化しちゃうじゃん? それを、赤外線とか可視光線を合体させて、もっとキレイにするのが画像融合(がぞうゆうごう)だよ!
    • 方法: ControlFusion は、劣化を物理的にシミュレーション! あと、言葉で「もっと明るくして!」とか命令できるようにしたんだって!
    • 結果: どんなに画像が劣化してても、ユーザーの希望通りに修正できるってこと! どんな場面でも最高の画質になるってワケ💖
    • 意義: いろんな分野で使えるから、IT業界がめっちゃ進化するチャンス! 最高の技術じゃん?
  4. リアルでの使いみちアイデア💡

    • 街の防犯カメラの映像を鮮明にして、犯罪を未然に防ぐ!
    • 車の自動運転をもっと安全にして、事故を減らす!

続きは「らくらく論文」アプリで

ControlFusion: A Controllable Image Fusion Framework with Language-Vision Degradation Prompts

Linfeng Tang / Yeda Wang / Zhanchuan Cai / Junjun Jiang / Jiayi Ma

Current image fusion methods struggle to address the composite degradations encountered in real-world imaging scenarios and lack the flexibility to accommodate user-specific requirements. In response to these challenges, we propose a controllable image fusion framework with language-vision prompts, termed ControlFusion, which adaptively neutralizes composite degradations. On the one hand, we develop a degraded imaging model that integrates physical imaging mechanisms, including the Retinex theory and atmospheric scattering principle, to simulate composite degradations, thereby providing potential for addressing real-world complex degradations from the data level. On the other hand, we devise a prompt-modulated restoration and fusion network that dynamically enhances features with degradation prompts, enabling our method to accommodate composite degradation of varying levels. Specifically, considering individual variations in quality perception of users, we incorporate a text encoder to embed user-specified degradation types and severity levels as degradation prompts. We also design a spatial-frequency collaborative visual adapter that autonomously perceives degradations in source images, thus eliminating the complete dependence on user instructions. Extensive experiments demonstrate that ControlFusion outperforms SOTA fusion methods in fusion quality and degradation handling, particularly in countering real-world and compound degradations with various levels. The source code is publicly available at https://github.com/Linfeng-Tang/ControlFusion.

cs / cs.CV