Showing cs.CVShow all
2 papers · 1 filter
cs.CV2024★ 1 cited
Seek for Incantations: Towards Accurate Text-to-Image Diffusion Synthesis through Prompt Engineering
Chang Yu, Junran Peng, Xiangyu Zhu +3
The text-to-image synthesis by diffusion models has recently shown remarkable performance in generating high-quality images. Although performs well for simple texts, the models may…
cs.CV2023
Graphics Capsule: Learning Hierarchical 3D Face Representations from 2D Images
Chang Yu, Xiangyu Zhu, Xiaomei Zhang +2
The function of constructing the hierarchy of objects is important to the visual process of the human brain. Previous studies have successfully adopted capsule networks to decompos…