2025/12/26 by Zhibin Qin, Qin, Zhibin, Zhenxiong Tan +7
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #Advanced Image Fusion Techniques #Cell Image Analysis Techniques #Computation #Encoding (memory) #Fidelity #Generative Adversarial Networks and Image Synthesis #High fidelity #Image editing #Redundancy (engineering) #Reuse #Transformer
paper · open access · doi:10.48550/arxiv.2512.22323
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/12/26 · openalex created_date 2025/12/31 · openalex updated_date 2026/07/28
Diffusion Transformer models have significantly advanced image editing by encoding conditional images and integrating them into transformer layers. However, most edits involve modifying only small regions, while current methods uniformly process and denoise all tokens at every timestep, causing redundant computation and potentially degrading unchanged areas. This raises a fundamental question: Is it truly necessary to regenerate every region during editing? To address this, we propose SpotEdit, a training-free diffusion editing framework that selectively updates only the modified regions. SpotEdit comprises two key components: SpotSelector identifies stable regions via perceptual similarity and skips their computation by reusing conditional image features; SpotFusion adaptively blends these features with edited tokens through a dynamic fusion mechanism, preserving contextual coherence and editing quality. By reducing unnecessary computation and maintaining high fidelity in unmodified areas, SpotEdit achieves efficient and precise image editing.