Addressing Attribute Leakages in Diffusion-based Image Editing without Training
Diffusion models have become a cornerstone in image editing, offering flexibility with language prompts and source images. However, a key challenge is attribute leakage, where unintended modifications occur in non-target regions or within target regions due to attribute interference. Existing methods often suffer from leakage due to naive text embeddings and inadequate handling of End-of-Sequence (EOS) token embeddings. To address this, we propose ALE-Edit (Attribute-leakage-free editing), a novel framework to minimize attribute leakage with three components: (1) Object-Restricted Embeddings (ORE) to localize object-specific attributes in text embeddings, (2) Region-Guided Blending for Cross-Attention Masking (RGB-CAM) to align attention with target regions, and (3) Background Blending (BB) to preserve non-edited regions. Additionally, we introduce ALE-Bench, a benchmark for evaluating attribute leakage with new metrics for target-external and target-internal leakage. Experiments demonstrate that our framework significantly reduces attribute leakage while maintaining high editing quality, providing an efficient and tuning-free solution for multi-object image editing.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeObjectMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
BindEdit: Taming Attention Leakage for Precise Multi-Object Image Editing
Real image editing enables precise manipulation of visual content, yet existing methods often fail in complex multi-object scenarios, causing semantic blending, object duplication, or incomplete edits. We attribute these…
Image EditingAttDiff-GAN: A Hybrid Diffusion-GAN Framework for Facial Attribute Editing
Facial attribute editing aims to modify target attributes while preserving attribute-irrelevant content and overall image fidelity. Existing GAN-based methods provide favorable controllability, but often suffer from weak…
Image GenerationLayerDiffusion: Layered Controlled Image Editing with Diffusion Models
Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, …
Attributetext-guided-image-editingExploring Attribute Variations in Style-based GANs using Diffusion Models
Existing attribute editing methods treat semantic attributes as binary, resulting in a single edit per attribute. However, attributes such as eyeglasses, smiles, or hairstyles exhibit a vast range of diversity. In this w…
AttributeDenoisingDiversityEditable Generative Adversarial Networks: Generating and Editing Faces Simultaneously
We propose a novel framework for simultaneously generating and manipulating the face images with desired attributes. While the state-of-the-art attribute editing technique has achieved the impressive performance for crea…
AttributeFace Generation