Press ESC to close

3D diffusion models

Freetalker: Controllable Speech and Text-Driven Gesture Generation Based on Diffusion Models for Enhanced Speaker Naturalness

root 0

The article presents ‘FreeTalker’, a novel framework that generates both spontaneous and non-spontaneous speaker motions, thus improving the naturalness and controllability of talking avatars. Unlike previous models, which only considered…

Continue reading

MAG-Edit: Localized Image Editing in Complex Scenarios via $\underline{M}$ask-Based $\underline{A}$ttention-Adjusted $\underline{G}$uidance

root 0

The MAG-Edit method enables localized image editing in complex scenarios. This training-free, inference-stage optimization method optimizes the noise latent feature in diffusion models by maximizing two mask-based cross-attention constraints of…

Continue reading