The image depicts a visual diagram filled with various concepts and technologies in the field of video generation. The diagram is divided into several sections, each containing a different topic or technology. The sections are arranged in a circular shape, with each segment containing multiple sub-segments. The diagram is surrounded by a person, possibly the person who created the diagram, who is also described in the caption as being "sharing his insights." The person is wearing a tie, which is mentioned in the caption as being "casual." The overall scene suggests that the person is presenting the diagram to a group or audience, possibly at a workshop or conference.
Text transcribed from the image:
2.2
en-Source
se Models
-1
2023
LaVie
Wang et al. 2023
after
2023
Video Diffusion
mann et al. 2023
delScopeT2V
ang et al. 2023
2.3
Other Closed-Source
Works
VideoFactory
Wang et al. 2023
VideoFusion
Luo et al. 2023
Latent-Shift
VDM
Ho et al. 2022
An et al. 2023
PYoCo
Ge et al. 2023
2.4
NEXT-GPT
Xing et al. 2023
Training-Efficient
Techniques
AnimateDiff
Guo et al. 2023
DSDN
Liu et al. 2023
Text2Video-Zero
Khachatryan et al. 2023
2.1
Pioneering Works
Imagen Video
Ho et al. 2022
Align your Latents
Blattmann et al. 2023
Make-A-Video
Singer et al. 2022
MagicVideo
Zhou et al. 2022
SimDA
Xing et al. 2022
Generative Disco
Liu et al. 2023
AADiff
Lee et al. 2023
MCDiff
Chen et al. 2023
MovieFactory
Zhu et al. 2023
2.5
Storyboard
2.7
Multimodal-Guided
Generation
TPOS
Jeong et al. 2023
VideoDirectorGPT LLM-Grounded
Lin et al. 2023
VisorGPT
Xie et al. 2023
DirecT2V
Hong et al. 2023
Free-Bloom
Huang et al. 2023
Dysen-VDM
Video
Generation
Fei et al. 2023
VDM
Lian et al. 2023
2.6
Long Video
Generation
LVDM
He et al. 2022
VidRF
Gu et al. 2023
DragNUWA
Yin et al. 2023
CoDi
Tang et al. 2023
VideoGen
Li et al. 2023
NUWA-XL
Yin et al. 2023
MM-Diffusion
Ruan et al. 2023
LFDM
Ni et al. 2023
Generative Dynamics
Li et al. 2023
MinD-Video
Chen et al. 2023
9
Copyright@Mike Shou, NUS
10