Visual Object Networks: Image Generation with Disentangled 3D Representations
Jun-Yan Zhu, Zhoutong Zhang, Chengkai Zhang, Jiajun Wu, Antonio Torralba, Josh Tenenbaum, Bill Freeman
–Neural Information Processing Systems
However,while existing models cansynthesize photorealistic images, they lack an understanding of our underlying 3D world. We present a new generative model,Visual Object Networks (VON), synthesizing natural images of objects with a disentangled 3D representation.
Neural Information Processing Systems
Feb-13-2026, 18:55:13 GMT
- Country:
- Asia > Japan
- Honshū > Chūbu > Ishikawa Prefecture > Kanazawa (0.05)
- North America > Canada
- Asia > Japan
- Technology: