Work

LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation

Year: 2017

Type: preprint

Abstract: We present LR-GAN: an adversarial image generation model which takes scene structure and context into account. Unlike previous generative adversarial networks (GANs), the proposed GAN learns to generate image background and foregrounds separately and recursively, and stitch the foregrounds on the background in a contextually relevant manner to produce a complete natural image. For each foreground, the model learns to generate its appearance, shape and pose. The whole model is unsupervised, and is trained in an end-to-end manner with gradient descent methods. The experiments demonstrate that LR-GAN can generate more natural images with objects that are more human recognizable than DCGAN.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1703.01560

Authors: Yang, Jianwei, Kannan, Anitha, Batra, Dhruv, Parikh, Devi

Institutions: Virginia Tech, Meta (United States), Georgia Institute of Technology

Language: English

Topic: Generative Adversarial Networks and Image Synthesis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2592101326

Cites:

Cited by: 187

Related to: 10