paper-with-me

홈 › Papers

Addressing Attribute Leakages in Diffusion-based Image Editing without Training

2024-12-06 · Sunung Mun, Jinhwan Nam, Sunghyun Cho, Jungseul Ok

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.

📄 PDF Abstract BibTeX arXiv:2412.04715

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeObject

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

BindEdit: Taming Attention Leakage for Precise Multi-Object Image Editing

2026-06-17 · Chaewon Park, Soyoon Lee, Naeun Lee, Minjung Shin 외 arxiv

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 Editing

AttDiff-GAN: A Hybrid Diffusion-GAN Framework for Facial Attribute Editing

2026-04-23 · Wenmin Huang, Weiqi Luo, Xiaochun Cao, Jiwu Huang arxiv

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 Generation

LayerDiffusion: Layered Controlled Image Editing with Diffusion Models

2023-05-30 · Pengzhi Li, QInxuan Huang, Yikang Ding, Zhiheng Li

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-editing

Exploring Attribute Variations in Style-based GANs using Diffusion Models

2023-11-27 · Rishubh Parihar, Prasanna Balaji, Raghav Magazine, Sarthak Vora 외

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…

AttributeDenoisingDiversity

Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously

2018-07-20 · Kyungjune Baek, Duhyeon Bang, Hyunjung Shim

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