A5101237767- Generative Adversarial Networks and Image Synthesis
- Advanced Image and Video Retrieval Techniques
- Human Motion and Animation
- Video Analysis and Summarization
- Augmented Reality Applications
- Advanced Vision and Imaging
- Multimodal Machine Learning Applications
Beijing University of Posts and Telecommunications
2023-2025
Touchscreen IoT devices, such as smartphones and tablets, have been seamlessly integrated into our daily lives. Drawing sketches on the touch screen is an extremely convenient mode of interaction, when combined with generative AI, it makes customized data generation digital twin based devices more straightforward. However, scarcity free-hand sketch construction data-driven AI models a thorny issue. Despite emergence some large-scale datasets, these datasets primarily consist at single-object...
The scarcity of free-hand sketch presents a challenging problem. Despite the emergence some large-scale datasets, these datasets primarily consist sketches at single-object level. There continues to be lack paired for scene sketches. In this paper, we propose self-supervised method generation that does not rely on any existing sketch, enabling transformation into To accomplish this, introduce vector captioning and semantic expansion. Additionally, design network incorporates fusion...
Sketch is an abstract visual representation that can be recovered as natural photographs in the human mind. Many researchers are drawn to work on translating sketches photographs. Since conventional sketch-to-image models designed generate images with a single object subject, generating scene image multiple classes of objects tricky problem. To tackle this challenge, we propose first generation method based diffusion models. Our model uses encoder summarize contour and class features sketch...