ResEdit: 精密な生成的画像編集のための残差埋め込み
ResEdit: Residual embeddings for precise generative image editing
拡散画像生成モデルを反転により編集に応用し、残差画像エンコーディングを追加条件として最適化することで、画像の同一性保持と編集可能性を両立させる手法を提案した。
著者: Ahmet Canberk Baykal, Valentin Deschaintre, Yannick Hold-Geoffroy, Michael Fischer, Anna Frühstück, Cengiz Öztireli, Iliyan Georgiev
分類: cs.CV, cs.GR
原文アブストラクト
Conditional diffusion image generators can be repurposed for editing through inversion, without the need for large-scale paired fine-tuning data. However, producing high-quality, targeted edits while maintaining image identity and global consistency remains challenging, as weakly conditioned inversion often embeds conflicting image features into the noise. We demonstrate that incorporating a residual image encoding as additional conditioning enables both improved identity preservation and better editability. We optimize this residual encoding to provide a strong conditioning signal for reconstruction, thereby reducing the reliance on inversion and susceptibility to its aforementioned pitfalls. To ensure this residual does not interfere with desired edits, we incorporate a gradient reversal-based optimization strategy that disentangles the residual from the edited condition. We illustrate our method's ability to produce high-fidelity results across precise intrinsic-based editing and relighting, and show proof-of-concept text-guided manipulation.