Place: Adaptive layout-semantic fusion for semantic image synthesis

Z Lv, Y Wei, W Zuo, KYK Wong - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Recent advancements in large-scale pre-trained text-to-image models have led to
remarkable progress in semantic image synthesis. Nevertheless synthesizing high-quality …

Instruct2Attack: Language-Guided Semantic Adversarial Attacks

J Liu, C Wei, Y Guo, H Yu, A Yuille, S Feizi… - arXiv preprint arXiv …, 2023 - arxiv.org
We propose Instruct2Attack (I2A), a language-guided semantic attack that generates
semantically meaningful perturbations according to free-form language instructions. We …

SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis

H Gao, M Gao, J Li, W Li, R Zhi, H Tang… - European Conference on …, 2025 - Springer
Semantic image synthesis (SIS) shows good promises for sensor simulation. However,
current best practices in this field, based on GANs, have not yet reached the desired level of …

Novel Object Synthesis via Adaptive Text-Image Harmony

Z Xiong, Z Zhang, Z Chen, S Chen, X Li, G Sun… - arXiv preprint arXiv …, 2024 - arxiv.org
In this paper, we study an object synthesis task that combines an object text with an object
image to create a new object image. However, most diffusion models struggle with this …

SCP-Diff: Photo-Realistic Semantic Image Synthesis with Spatial-Categorical Joint Prior

H Gao, M Gao, J Li, W Li, R Zhi, H Tang… - arXiv preprint arXiv …, 2024 - arxiv.org
Semantic image synthesis (SIS) shows good promises for sensor simulation. However,
current best practices in this field, based on GANs, have not yet reached the desired level of …

Reconciling Semantic Controllability and Diversity for Remote Sensing Image Synthesis with Hybrid Semantic Embedding

J Liu, D Zhao, B Yuan, W Li, T Li - arXiv preprint arXiv:2411.14781, 2024 - arxiv.org
Significant advancements have been made in semantic image synthesis in remote sensing.
However, existing methods still face formidable challenges in balancing semantic …

Diverse Semantic Image Editing with Style Codes

H Sivuk, A Dundar - arXiv preprint arXiv:2309.13975, 2023 - arxiv.org
Semantic image editing requires inpainting pixels following a semantic map. It is a
challenging task since this inpainting requires both harmony with the context and strict …

A Deep Semantic Segmentation Network with Semantic and Contextual Refinements

Z Wang, D Liu, LY Wu, S Wang, X Guo, L Qi - arXiv preprint arXiv …, 2024 - arxiv.org
Semantic segmentation is a fundamental task in multimedia processing, which can be used
for analyzing, understanding, editing contents of images and videos, among others. To …

Separable Facial Image Editing via Warping with Displacement Vectors

R Nishikawa, C Gu, H Takahashi, S Kuriyama - IEEE Access, 2024 - ieeexplore.ieee.org
Recent deep learning techniques have enabled simple methods of image editing through
textual instructions; however, it remains challenging to perform specific and quantitative …

A New StyleGAN Latent Space Based Model for Image Style Transfer

R Dey, S Palaiahnakote, S Bhattacharya… - … Conference on Pattern …, 2025 - Springer
Cross-domain image style transfer task is an attractive topic for several applications, such as
image-to-image style transfer, text-to-image style transfer, artistic image generation, etc. In …