Big data and AI-driven product design: A survey
H Quan, S Li, C Zeng, H Wei, J Hu - Applied Sciences, 2023 - mdpi.com
As living standards improve, modern products need to meet increasingly diversified and
personalized user requirements. Traditional product design methods fall short due to their …
personalized user requirements. Traditional product design methods fall short due to their …
Controllable image synthesis methods, applications and challenges: a comprehensive survey
S Huang, Q Li, J Liao, S Wang, L Liu, L Li - Artificial Intelligence Review, 2024 - Springer
Abstract Controllable Image Synthesis (CIS) is a methodology that allows users to generate
desired images or manipulate specific attributes of images by providing precise input …
desired images or manipulate specific attributes of images by providing precise input …
Vision-language matching for text-to-image synthesis via generative adversarial networks
Text-to-image synthesis is an attractive but challenging task that aims to generate a photo-
realistic and semantic consistent image from a specific text description. The images …
realistic and semantic consistent image from a specific text description. The images …
Optimized GAN for text-to-image synthesis: Hybrid whale optimization algorithm and dragonfly algorithm
V Talasila, MR Narasingarao - Advances in Engineering Software, 2022 - Elsevier
Text to image synthesizes is a motivating and valuable task to explore in these days. The
objective is to produce images from texts or captions, ie considering textual descriptions as …
objective is to produce images from texts or captions, ie considering textual descriptions as …
Generative adversarial networks with adaptive semantic normalization for text-to-image synthesis
S Huang, Y Chen - Digital Signal Processing, 2022 - Elsevier
Transforming human natural language into photo-realistic images has always been a
challenging issue. Batch Normalization (BN) is used in current text-to-image models to …
challenging issue. Batch Normalization (BN) is used in current text-to-image models to …
Local-global visual interaction attention for image captioning
C Wang, X Gu - Digital Signal Processing, 2022 - Elsevier
Image captioning is a typical cross-modal task, which aims to automatically describe the
main content of an image with a complete and natural sentence. Existing attention based …
main content of an image with a complete and natural sentence. Existing attention based …
Text Conditioned Generative Adversarial Networks Generating Images and Videos: A Critical Review
Generative adversarial networks (GANs) have attained a lot of attention in the deep learning
community and have been in focus for the past few years. GAN finds its application in …
community and have been in focus for the past few years. GAN finds its application in …
Bi-LSTM based encoding and GAN for text-to-image synthesis
V Talasila, MR Narasingarao - Sensing and Imaging, 2022 - Springer
Synthesizing images from text is to produce images with reliable content as specified text
depiction that is an extremely demanding task with the most important problems like: content …
depiction that is an extremely demanding task with the most important problems like: content …
Adaptive multi-text union for stable text-to-image synthesis learning
Y Zhou, J Qian, H Zhang, X Xu, H Sun, F Zeng… - Pattern Recognition, 2024 - Elsevier
Abstract Generative Adversarial Networks (GANs) have significantly boosted the
performance of text-to-image generation tasks in recent years. To train the generator, losses …
performance of text-to-image generation tasks in recent years. To train the generator, losses …
An overview of controllable image synthesis: Current challenges and future trends
S Huang, Q Li, J Liao, L Liu, L Li - Available at SSRN 4187269, 2022 - papers.ssrn.com
Controllable image synthesis is a method by which users can manipulate a particular
attribute in an image in a semantically meaningful way without affecting other attributes. This …
attribute in an image in a semantically meaningful way without affecting other attributes. This …