360度屋内パノラマ編集に向けた、リフォーカス型クロスアテンションによるチューニング不要拡散モデル
Toward 360-Degree Indoor Panorama Editing via Tuning-Free Diffusion Model with Refocusing Cross-Attention
チューニング不要で対象領域のみを正確に編集できる拡散モデル編集手法FocusDiffを提案し、360度屋内パノラマ編集にも応用した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Dinh-Khoi Vo, Nhut-Thanh Le-Hinh, Viet-Tham Huynh, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le
分類: cs.CV
原文アブストラクト
Zero-shot text-guided diffusion has significantly advanced image editing; however, its practical usability remains constrained by three persistent challenges: prompt brittleness that requires meticulous prompt engineering, spillover edits that unintentionally affect non-target regions, and failures on small or cluttered objects caused by limited fine-grained supervision in training data. We propose FocusDiff (Target-Aware Refocusing for Tuning-Free Diffusion Editing), a tuning-free framework for precise and region-specific image manipulation based on refocusing cross-attention. Given a target region obtained through automated segmentation or manual selection, FocusDiff applies selective blurring to non-edit areas to guide attention toward the masked region while accurately transferring the object's identity, structure, and appearance to the edited output. Integrated context-preserving modules further ensure background fidelity and global coherence, enabling accurate edits from simple text prompts in a single pass. We also extend FocusDiff to 360-degree indoor panorama editing and demonstrate its effectiveness within virtual reality environments. Extensive experiments on our localized editing benchmark LIMB, comprising 30 multi-object images and 100 annotated examples including challenging small-object cases, show that FocusDiff outperforms existing zero-shot editors in text-image alignment and background preservation, achieving superior precision, photorealism, and usability. The project page is available at https://vdkhoi20.github.io/FocusDiff.
