The image depicts a person attending a presentation or meeting, with a poster paper displayed on the back of a chair. The poster paper appears to be a visual representation of a presentation or meeting, with the words "New Advances in Video Conferencing" written on it. There is also a television screen in the background, with a person sitting in front of it. The television is displaying a slide on a wire mesh, which appears to be the visual representation described in the image. There is a laptop on a table in the background, with a person sitting in front of it. The person is likely the one who is presenting the material on the poster paper. The image also shows a chair with a poster paper on the back of it, which appears to be the chair where the person is sitting.
Text transcribed from the image:
Text2Video-Zero
Use Stable Diffusion to generate videos without any finetuning
°
Optional background smoothing: regenerate the background, average with the first frame
~N(0,1)
z-DDIM Backward(2), At, SD)
)
DDPM Forward(At)
for &-2,3,
Text prompt: "A horse is galloping on the street-
Convolution
Cross-Frame Attention
Transformer Block x2
Salent Object
Detector
W
Background Smoothing
-Wa(z)
--
Step
for k 1,2 m, xT
Khachatryan et al., "Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators," arXiv 2023.
Copyright Mike Shou, NUS
117