Showing 2024Show all
3 papers · 1 filter
cs.CV2024
BodyMetric: Evaluating the Realism of Human Bodies in Text-to-Image Generation
Nefeli Andreou, Varsha Vivek, Ying Wang +5
Accurately generating images of human bodies from text remains a challenging problem for state of the art text-to-image models. Commonly observed body-related artifacts include ext…
cs.CV2024
Analysis of Classifier-Free Guidance Weight Schedulers
Xi Wang, Nicolas Dufour, Nefeli Andreou +4
Classifier-Free Guidance (CFG) enhances the quality and condition adherence of text-to-image diffusion models. It operates by combining the conditional and unconditional prediction…
cs.CV2024
LEAD: Latent Realignment for Human Motion Diffusion
Nefeli Andreou, Xi Wang, Victoria Fernández Abrevaya +3
Our goal is to generate realistic human motion from natural language. Modern methods often face a trade-off between model expressiveness and text-to-motion alignment. Some align te…