Header logo is avg

Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis

2020

Conference Paper

avg


In recent years, Generative Adversarial Networks have achieved impressive results in photorealistic image synthesis. This progress nurtures hopes that one day the classical rendering pipeline can be replaced by efficient models that are learned directly from images. However, current image synthesis models operate in the 2D domain where disentangling 3D properties such as camera viewpoint or object pose is challenging. Furthermore, they lack an interpretable and controllable representation. Our key hypothesis is that the image generation process should be modeled in 3D space as the physical world surrounding us is intrinsically three-dimensional. We define the new task of 3D controllable image synthesis and propose an approach for solving it by reasoning both in 3D space and in the 2D image domain. We demonstrate that our model is able to disentangle latent 3D factors of simple multi-object scenes in an unsupervised fashion from raw images. Compared to pure 2D baselines, it allows for synthesizing scenes that are consistent wrt. changes in viewpoint or object pose. We further evaluate various 3D representations in terms of their usefulness for this challenging task.

Author(s): Yiyi Liao and Katja Schwarz and Lars Mescheder and Andreas Geiger
Book Title: Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Year: 2020

Department(s): Autonomous Vision
Bibtex Type: Conference Paper (inproceedings)

Event Name: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2020
Event Place: Seattle, USA

Links: pdf
suppmat
Video
Project Page
Video:

BibTex

@inproceedings{Liao2020CVPR,
  title = {Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis},
  author = {Liao, Yiyi and Schwarz, Katja and Mescheder, Lars and Geiger, Andreas},
  booktitle = { Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020}
}