SeamEdit: A Black-Box VLM-Agnostic Pipeline for Large-Image Semantic Editing
Semantic region editing for large images must satisfy two requirements at the same time: high generative quality and natural integration with surrounding content. Some related methods rely on white-box models and leave the strong generation capability of closed-source models underexplored. Directly applying closed-source models to tiled editing, however, introduces several failure modes: semantic deformation, canvas-level alignment drift, and visible seam artifacts. This paper presents SeamEdit, a training-free and model-agnostic pipeline that treats any VLM with inpainting capability as a black-box oracle. SeamEdit mitigates these issues through a five-stage post-hoc pipeline: overlay-based tile decomposition, black-box VLM inpainting, geometric and color-consistency correction, seam-risk-based multi-candidate ranking, and dynamic-programming curved seam fusion. The pipeline reduces seam visibility and supports semantic modification of arbitrary tile regions.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI
Data scarcity and noise are important issues in industrial applications of machine learning. However, it is often challenging to devise a scalable and generalized approach to address the fundamental distributional and se…
BIG-bench Machine LearningData Valuationimage-classificationImage ClassificationMIRAGE: Model-agnostic Industrial Realistic Anomaly Generation and Evaluation for Visual Anomaly Detection
Industrial visual anomaly detection (VAD) methods are typically trained on normal samples only, yet performance improves substantially when even limited anomalous data is available. Existing anomaly generation approaches…
Anomaly DetectionChange DetectionImage GenerationA Utility-preserving De-identification Pipeline for Cross-hospital Radiology Data Sharing
Large-scale radiology data are critical for developing robust medical AI systems. However, sharing such data across hospitals remains heavily constrained by privacy concerns. Existing de-identification research in radiol…
MedGrad E-CLIP: Enhancing Trust and Transparency in AI-Driven Skin Lesion Diagnosis
As deep learning models gain attraction in medical data, ensuring transparent and trustworthy decision-making is essential. In skin cancer diagnosis, while advancements in lesion detection and classification have improve…
DiagnosticLesion DetectionMedical Image AnalysisDebiased Noise Editing on Foundation Models for Fair Medical Image Classification
In the era of Foundation Models' (FMs) rising prominence in AI, our study addresses the challenge of biases in medical images while the model operates in black-box (e.g., using FM API), particularly spurious correlations…
ClassificationFairnessimage-classificationImage Classification+1