Goto

Collaborating Authors

 ztexture


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.