Advances in diffusion models for image data augmentation: A review of methods, models, evaluation metrics and future research directions

P Alimisis, I Mademlis, P Radoglou-Grammatikis… - Artificial Intelligence …, 2025 - Springer
Image data augmentation constitutes a critical methodology in modern computer vision
tasks, since it can facilitate towards enhancing the diversity and quality of training datasets; …

Colorpeel: Color prompt learning with diffusion models via color and shape disentanglement

MA Butt, K Wang, J Vazquez-Corral… - European Conference on …, 2024 - Springer
Abstract Text-to-Image (T2I) generation has made significant advancements with the advent
of diffusion models. These models exhibit remarkable abilities to produce images based on …

A survey on knowledge-enhanced multimodal learning

M Lymperaiou, G Stamou - Artificial Intelligence Review, 2024 - Springer
Multimodal learning has been a field of increasing interest, aiming to combine various
modalities in a single joint representation. Especially in the area of visiolinguistic (VL) …

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

C Tang, K Wang, F Yang, J van de Weijer - arxiv preprint arxiv …, 2024 - arxiv.org
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 …

ERDDCI: Exact Reversible Diffusion via Dual-Chain Inversion for High-Quality Image Editing

J Dai, Y Zhang, S Chen, J Yang, L Luo - arxiv preprint arxiv:2410.14247, 2024 - arxiv.org
Diffusion models (DMs) have been successfully applied to real image editing. These models
typically invert images into latent noise vectors used to reconstruct the original images …

GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models

L Kang, F Yang, K Wang, MA Souibgui, L Gomez… - ECAI 2024, 2024 - ebooks.iospress.nl
Fonts are integral to creative endeavors, design processes, and artistic productions. The
appropriate selection of a font can significantly enhance artwork and endow advertisements …