paper-with-me

Papers

LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation

2023-02-16 · Jiaxin Cheng, Xiao Liang, Xingjian Shi, Tong He, Tianjun Xiao, Mu Li

Layout-to-image generation refers to the task of synthesizing photo-realistic images based on semantic layouts. In this paper, we propose LayoutDiffuse that adapts a foundational diffusion model pretrained on large-scale image or text-image datasets for layout-to-image generation. By adopting a novel neural adaptor based on layout attention and task-aware prompts, our method trains efficiently, generates images with both high perceptual quality and layout alignment, and needs less data. Experiments on three datasets show that our method significantly outperforms other 10 generative models based on GANs, VQ-VAE, and diffusion models.

📄 PDF Abstract BibTeX arXiv:2302.08908

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationLayout-to-Image Generation

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…
VQ-VAE VQ-VAE is a type of variational autoencoder that uses vector quantisation to obtain a discrete latent representation. It differs from…

Similar Papers 제목 키워드 기반

Layered Rendering Diffusion Model for Controllable Zero-Shot Image Synthesis

2023-11-30 · Zipeng Qi, Guoxi Huang, Chenyang Liu, Fei Ye

This paper introduces innovative solutions to enhance spatial controllability in diffusion models reliant on text queries. We first introduce vision guidance as a foundational spatial cue within the perturbed distributio…

DenoisingImage Generation

LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation

2023-03-30 · CVPR 2023 1 · Guangcong Zheng, Xianpan Zhou, XueWei Li, Zhongang Qi 외

Recently, diffusion models have achieved great success in image synthesis. However, when it comes to the layout-to-image generation where an image often has a complex scene of multiple objects, how to make strong control…

Image GenerationLayout-to-Image GenerationObject

SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion

2026-07-06 · Paul Engstler, Iro Laina, Christian Rupprecht, Andrea Vedaldi arxiv

We present SynCity 3000, a framework for generating 3D scenes that are globally coherent while enabling fine-grained layout control. Building on the ability of current image-to-3D generators to produce complex 3D assets …

Scene Generation

Reason out Your Layout: Evoking the Layout Master from Large Language Models for Text-to-Image Synthesis

2023-11-28 · Xiaohui Chen, Yongfei Liu, Yingxiang Yang, Jianbo Yuan 외

Recent advancements in text-to-image (T2I) generative models have shown remarkable capabilities in producing diverse and imaginative visuals based on text prompts. Despite the advancement, these diffusion models sometime…

Image Generation

Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation

2024-01-01 · CVPR 2024 1 · Mohammad Amin Shabani, Zhaowen Wang, Difan Liu, Nanxuan Zhao 외

This paper proposes an image-vector dual diffusion model for generative layout design. Distinct from prior efforts that mostly ignore element-level visual information our approach integrates the power of a pre-traine…

Layout DesignLayout GenerationPosition