paper-with-me

홈 › Papers

SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidance

2024-05-24 · Guibao Shen, Luozhou Wang, Jiantao Lin, Wenhang Ge, Chaozhe Zhang, Xin Tao, Yuan Zhang, Pengfei Wan, Zhongyuan Wang, Guangyong Chen, Yijun Li, Ying-Cong Chen

Recent advancements in text-to-image generation have been propelled by the development of diffusion models and multi-modality learning. However, since text is typically represented sequentially in these models, it often falls short in providing accurate contextualization and structural control. So the generated images do not consistently align with human expectations, especially in complex scenarios involving multiple objects and relationships. In this paper, we introduce the Scene Graph Adapter(SG-Adapter), leveraging the structured representation of scene graphs to rectify inaccuracies in the original text embeddings. The SG-Adapter's explicit and non-fully connected graph representation greatly improves the fully connected, transformer-based text representations. This enhancement is particularly notable in maintaining precise correspondence in scenarios involving multiple relationships. To address the challenges posed by low-quality annotated datasets like Visual Genome, we have manually curated a highly clean, multi-relational scene graph-image paired dataset MultiRels. Furthermore, we design three metrics derived from GPT-4V to effectively and thoroughly measure the correspondence between images and scene graphs. Both qualitative and quantitative results validate the efficacy of our approach in controlling the correspondence in multiple relationships.

📄 PDF Abstract BibTeX arXiv:2405.15321

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

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

UNIC-Adapter: Unified Image-instruction Adapter with Multi-modal Transformer for Image Generation

2024-12-25 · CVPR 2025 1 · Lunhao Duan, Shanshan Zhao, Wenjun Yan, Yinglun Li 외

Recently, text-to-image generation models have achieved remarkable advancements, particularly with diffusion models facilitating high-quality image synthesis from textual descriptions. However, these models often struggl…

Image GenerationText to Image GenerationText-to-Image Generation

NightAdapter: Learning a Frequency Adapter for Generalizable Night-time Scene Segmentation

2025-01-01 · CVPR 2025 1 · Qi Bi, Jingjun Yi, Huimin Huang, Hao Zheng 외

Night-time scene segmentation is a critical yet challenging task in the real-world applications, primarily due to the complicated lighting conditions. However, existing methods lack sufficient generalization ability …

Scene Segmentation

SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models

2023-05-09 · Shanshan Zhong, Zhongzhan Huang, Wushao Wen, Jinghui Qin 외

Diffusion models, which have emerged to become popular text-to-image generation models, can produce high-quality and content-rich images guided by textual prompts. However, there are limitations to semantic understanding…

Image GenerationKnowledge Distillationparameter-efficient fine-tuningText to Image Generation+1

VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization

2024-04-30 · Yuliang Liu, Mingxin Huang, Hao Yan, Linger Deng 외

Text spotting, a task involving the extraction of textual information from image or video sequences, faces challenges in cross-domain adaption, such as image-to-image and image-to-video generalization. In this paper, we …

Domain AdaptationDomain GeneralizationText Spotting

FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer

2026-04-11 · Shenghe Zheng, Minyu Zhang, Tianhao Liu, Hongzhi Wang arxiv

With the growing availability of open-sourced adapters trained on the same diffusion backbone for diverse scenes and objects, combining these pretrained weights enables low-cost customized generation. However, most exist…

Image GenerationText GenerationStyle Transfer