Place: Adaptive layout-semantic fusion for semantic image synthesis
Recent advancements in large-scale pre-trained text-to-image models have led to
remarkable progress in semantic image synthesis. Nevertheless synthesizing high-quality …
remarkable progress in semantic image synthesis. Nevertheless synthesizing high-quality …
Instruct2Attack: Language-Guided Semantic Adversarial Attacks
We propose Instruct2Attack (I2A), a language-guided semantic attack that generates
semantically meaningful perturbations according to free-form language instructions. We …
semantically meaningful perturbations according to free-form language instructions. We …
SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis
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 …
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
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 …
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
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 …
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 …
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 …
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 …
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 …
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 …
image-to-image style transfer, text-to-image style transfer, artistic image generation, etc. In …