2025/12/17 by Zhou, Shengxiao, Li, Chenghua, Huang, Jianhao +2
Biochemistry, Genetics and Molecular Biology · Computer Science · #Cell Image Analysis Techniques #Feature (linguistics) #Fidelity #Handwritten Text Recognition Techniques #Key (lock) #Machine Learning and Data Classification #Mechanism (biology) #Perspective (graphical) #Probabilistic logic #Salient #Semantics (computer science)
paper · open access · doi:10.48550/arxiv.2512.15138
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/12/17 · openalex created_date 2025/12/19 · openalex updated_date 2026/07/28
Reference-guided instance editing is fundamentally limited by semantic entanglement, where a reference's intrinsic appearance is intertwined with its extrinsic attributes. The key challenge lies in disentangling what information should be borrowed from the reference, and determining how to apply it appropriately to the target. To tackle this challenge, we propose GENIE, a Generalizable Instance Editing framework capable of achieving explicit disentanglement. GENIE first corrects spatial misalignments with a Spatial Alignment Module (SAM). Then, an Adaptive Residual Scaling Module (ARSM) learns what to borrow by amplifying salient intrinsic cues while suppressing extrinsic attributes, while a Progressive Attention Fusion (PAF) mechanism learns how to render this appearance onto the target, preserving its structure. Extensive experiments on the challenging AnyInsertion dataset demonstrate that GENIE achieves state-of-the-art fidelity and robustness, setting a new standard for disentanglement-based instance editing.