VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling
Paper
•
2503.15855
•
Published
•
4
Hyojun GO
HJGO
AI & ML interests
VLP, Diffusion Models
Recent Activity
commented on
a paper
24 days ago
VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a
Video Generator
upvoted
a
paper
7 months ago
TextCrafter: Accurately Rendering Multiple Texts in Complex Visual
Scenes
Organizations
None yet
authored
a
paper
8 months ago
authored
3
papers
almost 2 years ago