日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

週刊ニュースレター購読
画像編集arXiv:2606.09901v1

拡散編集における制御性と忠実性のフロンティアについて

On the Controllability-Fidelity Frontier in Diffusion Editing

シェア:XThreadsFacebookLINEはてブBluesky

拡散モデルによる画像編集の制御性と忠実性のトレードオフを理論的・実証的に分析し、編集手法の限界と安全対策を提案する論文。

著者: Yi Hu, Leying Yi, Emily Davis, Finn Carter

分類: cs.GR, cs.CV, cs.HC, cs.LG, cs.MM

原文アブストラクト

Diffusion-based generative models enable powerful image editing capabilities, but achieving precise control while maintaining fidelity and safety remains challenging. We present a comprehensive theoretical and empirical study of controllable diffusion-based image editing, analyzing the trade-offs between adherence to user intent, preservation of non-target content, and output quality. Our work spans text- and mask-guided edits, point/drag manipulation, and inversion-based pipelines. We derive mathematical formulations of editing objectives and analyze dynamics of noise injection, score guidance, and inversion error. We provide theoretical bounds on reconstruction error, stability under repeated edits, and locality of changes. We propose algorithmic frameworks (with pseudocode) for mask-localized and instruction-guided editing, and present extensive experiments comparing state-of-the-art methods (e.g.\ TF-ICON \cite{lu2023tficone}, DragFlow \cite{zhou2025dragflow}, InstructPix2Pix \cite{brooks2023instructpix2pix}, UltraEdit \cite{zhao2024ultraedit}) on multiple tasks and metrics (FID, identity similarity, CLIP alignment, artifact scores, etc). Our results reveal key failure modes, such as identity drift, prompt sensitivity, and compositional errors. We also discuss ethical considerations in image editing, including misuse risks, bias, consent, and concept erasure techniques (e.g.\ MACE \cite{lu2024mace}, ANT \cite{li2025ant}, EraseAnything \cite{gao2024eraseanything}) as safeguards. We conclude with best practices and future directions for responsible, high-fidelity diffusion-based editing.

関連論文