4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling

Sherwin Bahmani1,2   Ivan Skorokhodov3,4   Victor Rong1,2   Gordon Wetzstein5   Leonidas Guibas5 
Peter Wonka3   Sergey Tulyakov4   Jeong Joon Park6   Andrea Tagliasacchi1,7,8   David B. Lindell1,2  
1 University of Toronto 2 Vector Institute 3 KAUST 4 Snap Inc. 5 Stanford University 6 University of Michigan 7 SFU 8 Google
Paper Code Project

Gallery

a space shuttle launching
a crocodile playing a drum set
a bear driving a car
an emoji of a baby panda reading a book
a panda dancing
a silver humanoid robot flipping a coin
a humanoid robot playing the violin
a dog wearing a superhero outfit with red cape flying through the sky
3D rendering of a fox playing videogame
a goat drinking beer
a panda playing on a swing set
unicorn running
a cat singing
a monkey eating a candy bar
baby panda eating ice cream
an alien playing the piano
a dog riding a skateboard
water spraying out of a firehydrant
a building on fire
a bulldog wearing a black pirate hat eating candy
a firepit
a lemur holding and drinking boba
a lightning hitting a building
a steam engine train is emitting steam into the air
an astronaut riding a horse
corgi running on grass
cute small cat sitting eating chicken wiggs watching a movie
darth vader surfing
darth vader with a flame thrower
dog running on grass
samurai swinging a katana in one hand
tesla trooper shooting lightning

Citation

@article{bah20244dfy,
  author = {Bahmani, Sherwin and Skorokhodov, Ivan and Rong, Victor and Wetzstein, Gordon and Guibas, Leonidas and Wonka, Peter and Tulyakov, Sergey and Park, Jeong Joon and Tagliasacchi, Andrea and Lindell, David B.},
  title = {4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling},
  journal = {IEEE Conference on Computer Vision and Pattern Recognition ({CVPR})},
  year = {2024},
}