VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control
1University of Toronto
2Vector Institute
3Snap Inc.
4SFU
arXiv 2024
RealEstate10K Test Set Generalization
Camera Input
Reference Trajectory Video
Camera Controlled Generation
A trio of fashionable, beret-clad cats sips coffee at a chic Parisian cafe
An astronaut cooking with a pan and fire in the kitchen
A cat sits at a grand piano, its paws gracefully tapping the keys
A huge dinosaur skeleton is walking in a golden wheat field on a bright sunny day
A man with a skull face in flames walking around Piccadilly circus
Otters with chef hats, skillfully preparing a miniature sushi feast on a lily pad
An astronaut feeding ducks on a sunny afternoon, reflection from the water
Cats engage in a strategic chess match on an ornate board
In a chic urban kitchen, a cat donned in a chef's hat expertly kneads dough on a marble countertop
In a potter's studio, skilled hands mold clay into a delicate sculpture
Melting ice cream dripping down the cone
3 sheep enjoying spaghetti together
A burning volcano
A cat wearing sunglasses and working as a lifeguard at a pool
A cat, dressed in detective attire, examines a magnifying glass over a crime scene made of scattered yarn
A chihuahua in astronaut suit and sunglasses floating in space
A couple enjoys a romantic gondola ride in Venice, Italy
A cute golden hamster throwing punches wearing pair of boxing gloves in a boxing ring
A hamster wearing virtual reality headsets is a dj in a disco
A Corgi dog riding a bike in Times Square. It is wearing sunglasses and a beach hat
A mouse in renaissance clothing eating a cheese slice
A snowman in a Venetian gondola ride
A squirrel eating a burger
