paper-with-me

홈 › Papers

LocInv: Localization-aware Inversion for Text-Guided Image Editing

2024-05-02 · Chuanming Tang, Kai Wang, Fei Yang, Joost Van de Weijer

Large-scale Text-to-Image (T2I) diffusion models demonstrate significant generation capabilities based on textual prompts. Based on the T2I diffusion models, text-guided image editing research aims to empower users to manipulate generated images by altering the text prompts. However, existing image editing techniques are prone to editing over unintentional regions that are beyond the intended target area, primarily due to inaccuracies in cross-attention maps. To address this problem, we propose Localization-aware Inversion (LocInv), which exploits segmentation maps or bounding boxes as extra localization priors to refine the cross-attention maps in the denoising phases of the diffusion process. Through the dynamic updating of tokens corresponding to noun words in the textual input, we are compelling the cross-attention maps to closely align with the correct noun and adjective words in the text prompt. Based on this technique, we achieve fine-grained image editing over particular objects while preventing undesired changes to other regions. Our method LocInv, based on the publicly available Stable Diffusion, is extensively evaluated on a subset of the COCO dataset, and consistently obtains superior results both quantitatively and qualitatively.The code will be released at https://github.com/wangkai930418/DPL

📄 PDF Abstract BibTeX arXiv:2405.01496

Code (1)

wangkai930418/DPL 공식 구현 pytorch

Tasks

Denoisingtext-guided-image-editing

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
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

Wavelet-Guided Semantic Signal Compensation for Inversion-Free Image Editing

2026-07-02 · Anqi Tang, Wenhao Sun, Zhaoqiang Liu arxiv

Text-guided image editing aims to modify visual content according to a target prompt while preserving the background. Recent inversion-free image editing frameworks such as FlowEdit have demonstrated strong editing capab…

Image Editing

Latent Inversion with Timestep-aware Sampling for Training-free Non-rigid Editing

2024-02-13 · Yunji Jung, Seokju Lee, Tair Djanibekov, Hyunjung Shim 외

Text-guided non-rigid editing involves complex edits for input images, such as changing motion or compositions within their surroundings. Since it requires manipulating the input structure, existing methods often struggl…

Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

2025-08-11 · Zeqian Long, Mingzhe Zheng, Kunyu Feng, Xinhua Zhang 외 arxiv

While recent flow-based image editing models demonstrate general-purpose capabilities across diverse tasks, they often struggle to specialize in challenging scenarios -- particularly those involving large-scale shape tra…

Image Editing

High-Fidelity Image Inpainting with Multimodal Guided GAN Inversion

2025-04-17 · Libo Zhang, Yongsheng Yu, Jiali Yao, Heng Fan

Generative Adversarial Network (GAN) inversion have demonstrated excellent performance in image inpainting that aims to restore lost or damaged image texture using its unmasked content. Previous GAN inversion-based metho…

Generative Adversarial NetworkImage InpaintingSemantic Segmentation

CaLDiff: Camera Localization in NeRF via Pose Diffusion

2023-12-23 · Rashik Shrestha, Bishad Koju, Abhigyan Bhusal, Danda Pani Paudel 외

With the widespread use of NeRF-based implicit 3D representation, the need for camera localization in the same representation becomes manifestly apparent. Doing so not only simplifies the localization process -- by avoid…

Camera LocalizationNeRF