A speaker presents a detailed slide on "Lumiere: A space-time diffusion model for video generation" during a conference. The room is equipped with modern lighting and ceiling fixtures, and a large screen displays complex diagrams and text. The presentation captures the attention of attendees, with one individual raising their smartphone to record or take a picture of the slide. Another attendee is seated on the floor, head bowed, possibly taking notes or reflecting on the content. A projector is positioned on a small round table to the left, indicating the use of multimedia in the presentation. The setting suggests a focus on innovation and emerging technologies.
Text transcribed from the image:
711
Lumiere
A space-time diffusion model for video generation
(e) Common Approach with TSR model(s)
128x128x16
S
128x128x30
16fps, Sacc
TSR
H
Base
TSR
(b) Our Approach
603)
SSR
SSR
SSR
SSR
SSR
1024x1024.5000000000
16,500
Bar-Tal et al, "Lumiere: A space-time diffusion model for video generation," arv 2024,
CLOME00
STUN
SSR
SSR
MaltiDiffusion
Copyright
813)