arXiv Analytics

Sign in

arXiv:1812.02725 [cs.CV]AbstractReferencesReviewsResources

Visual Object Networks: Image Generation with Disentangled 3D Representation

Jun-Yan Zhu, Zhoutong Zhang, Chengkai Zhang, Jiajun Wu, Antonio Torralba, Joshua B. Tenenbaum, William T. Freeman

Published 2018-12-06Version 1

Recent progress in deep generative models has led to tremendous breakthroughs in image generation. However, while existing models can synthesize 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. Inspired by classic graphics rendering pipelines, we unravel our image formation process into three conditionally independent factors---shape, viewpoint, and texture---and present an end-to-end adversarial learning framework that jointly models 3D shapes and 2D images. Our model first learns to synthesize 3D shapes that are indistinguishable from real shapes. It then renders the object's 2.5D sketches (i.e., silhouette and depth map) from its shape under a sampled viewpoint. Finally, it learns to add realistic texture to these 2.5D sketches to generate natural images. The VON not only generates images that are more realistic than state-of-the-art 2D image synthesis methods, but also enables many 3D operations such as changing the viewpoint of a generated image, editing of shape and texture, linear interpolation in texture and shape space, and transferring appearance across different objects and viewpoints.

Comments: NeurIPS 2018. Code: Website:
Categories: cs.CV, cs.GR, stat.ML
Related articles: Most relevant | Search more
arXiv:1904.12690 [cs.CV] (Published 2019-04-26)
Capturing human categorization of natural images at scale by combining deep networks and cognitive models
arXiv:1612.08185 [cs.CV] (Published 2016-12-24)
Deep Probabilistic Modeling of Natural Images using a Pyramid Decomposition
arXiv:1904.01326 [cs.CV] (Published 2019-04-02)
HoloGAN: Unsupervised learning of 3D representations from natural images