paper-with-me

홈 › Papers

Continuous Layout Editing of Single Images with Diffusion Models

2023-06-22 · Zhiyuan Zhang, Zhitong Huang, Jing Liao

Recent advancements in large-scale text-to-image diffusion models have enabled many applications in image editing. However, none of these methods have been able to edit the layout of single existing images. To address this gap, we propose the first framework for layout editing of a single image while preserving its visual properties, thus allowing for continuous editing on a single image. Our approach is achieved through two key modules. First, to preserve the characteristics of multiple objects within an image, we disentangle the concepts of different objects and embed them into separate textual tokens using a novel method called masked textual inversion. Next, we propose a training-free optimization method to perform layout control for a pre-trained diffusion model, which allows us to regenerate images with learned concepts and align them with user-specified layouts. As the first framework to edit the layout of existing images, we demonstrate that our method is effective and outperforms other baselines that were modified to support this task. Our code will be freely available for public use upon acceptance.

📄 PDF Abstract BibTeX arXiv:2306.13078

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

None 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…
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…

Similar Papers 제목 키워드 기반

Consistent Image Layout Editing with Diffusion Models

2025-03-09 · Tao Xia, Yudi Zhang, Ting Liu Lei Zhang

Despite the great success of large-scale text-to-image diffusion models in image generation and image editing, existing methods still struggle to edit the layout of real images. Although a few works have been proposed to…

Image Generation

MFTF: Mask-free Training-free Object Level Layout Control Diffusion Model

2024-12-02 · Shan Yang

Text-to-image generation models have revolutionized content creation, but diffusion-based vision-language models still face challenges in precisely controlling the shape, appearance, and positional placement of objects i…

DenoisingImage GenerationObjectText to Image Generation+1

Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors

2024-03-18 · Ruicheng Wang, Jianfeng Xiang, Jiaolong Yang, Xin Tong

We propose a novel image editing technique that enables 3D manipulations on single images, such as object rotation and translation. Existing 3D-aware image editing approaches typically rely on synthetic multi-view datase…

Novel View Synthesis

POCI-Diff: Position Objects Consistently and Interactively with 3D-Layout Guided Diffusion

2026-01-20 · Andrea Rigo, Luca Stornaiuolo, Weijie Wang, Mauro Martino 외 arxiv

We propose a diffusion-based approach for Text-to-Image (T2I) generation with consistent and interactive 3D layout control and editing. While prior methods improve spatial adherence using 2D cues or iterative copy-warp-p…

Move Anything with Layered Scene Diffusion

2024-04-10 · CVPR 2024 1 · Jiawei Ren, Mengmeng Xu, Jui-Chieh Wu, Ziwei Liu 외

Diffusion models generate images with an unprecedented level of quality, but how can we freely rearrange image layouts? Recent works generate controllable scenes via learning spatially disentangled latent codes, but thes…

DenoisingDisentanglement