Farm3D: learning articulated 3D animals by distilling 2D diffusion
We present Farm3D, a method to learn category-specific 3D reconstructors for articulated objects entirely from “free” virtual supervision from a pre-trained 2D diffusionbased image generator. Recent approaches can learn, given a collection of single-view images of an object category, a monocular net...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2024
|