Presentation Information

[3Dp1-21L]A Preliminary Study on Preserving Text Shapes in Diffusion Based Stereoscopic Video Generation from Monocular Images

*Kyosuke Yanagida1, Takafumi Koike1,2 (1. Hosei University (Japan), 2. RealImage Inc. (Japan))

Keywords:

Stereoscopic video generation,Diffusion model,Depth-layer decomposition


Comment

To browse or post comments, you must log in.Log in