paper-with-me

Papers

BEGAN: Boundary Equilibrium Generative Adversarial Networks

2017-03-31 · David Berthelot, Thomas Schumm, Luke Metz

We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. Additionally, it provides a new approximate convergence measure, fast and stable training and high visual quality. We also derive a way of controlling the trade-off between image diversity and visual quality. We focus on the image generation task, setting a new milestone in visual quality, even at higher resolutions. This is achieved while using a relatively simple model architecture and a standard training procedure.

📄 PDF Abstract BibTeX arXiv:1703.10717

Code (18)

Aggrathon/MtGan tf
Heumi/BEGAN-tensorflow tf
JimmyDoan1309/BEGAN---Tensorflow-implementation tf
artcg/BEGAN tf
carpedm20/BEGAN-tensorflow tf
conan7882/tf-gans tf
consequencesunintended/BEGAN tf
davidismael/BEGAN tf
eriklindernoren/PyTorch-GAN pytorch
evan11401/CS_IOC5008_0856043_HW2 pytorch
lvyufeng/MindSpore-GAN mindspore
mlvc-lab/BeGan_pytorch pytorch
taey16/pix2pixBEGAN.pytorch pytorch
tensorpack/tensorpack/tree/master/examples/GAN tf
timsainb/GAIA tf
vbnmzxc9513/GAN_BEGAN_human-face pytorch
vbnmzxc9513/GAN_BEGAN_hw2 pytorch
zhusiling/BEGAN_org pytorch

Tasks

DiversityImage Generation

Similar Papers 제목 키워드 기반

Escaping from Collapsing Modes in a Constrained Space

2018-08-22 · ECCV 2018 9 · Chia-Che Chang, Chieh Hubert Lin, Che-Rung Lee, Da-Cheng Juan 외

Generative adversarial networks (GANs) often suffer from unpredictable mode-collapsing during training. We study the issue of mode collapse of Boundary Equilibrium Generative Adversarial Network (BEGAN), which is one of …

Generative Adversarial NetworkImage Generation

Image Quality Assessment Techniques Show Improved Training and Evaluation of Autoencoder Generative Adversarial Networks

2017-08-06 · Michael O. Vertolli, Jim Davies

We propose a training and evaluation approach for autoencoder Generative Adversarial Networks (GANs), specifically the Boundary Equilibrium Generative Adversarial Network (BEGAN), based on methods from the image quality …

Generative Adversarial NetworkImage Quality Assessment

A study on the use of Boundary Equilibrium GAN for Approximate Frontalization of Unconstrained Faces to aid in Surveillance

2018-09-14 · Wazeer Zulfikar, Sebastin Santy, Sahith Dambekodi, Tirtharaj Dash

Face frontalization is the process of synthesizing frontal facing views of faces given its angled poses. We implement a generative adversarial network (GAN) with spherical linear interpolation (Slerp) for frontalization …

Face GenerationGenerative Adversarial Network

Image Quality Assessment Techniques Improve Training and Evaluation of Energy-Based Generative Adversarial Networks

2018-01-01 · ICLR 2018 1 · Michael O. Vertolli, Jim Davies

We propose a new, multi-component energy function for energy-based Generative Adversarial Networks (GANs) based on methods from the image quality assessment literature. Our approach expands on the Boundary Equilibrium Ge…

Generative Adversarial NetworkImage Quality Assessment

Solving Inverse Problems with Conditional-GAN Prior via Fast Network-Projected Gradient Descent

2021-09-02 · Muhammad Fadli Damara, Gregor Kornhardt, Peter Jung

The projected gradient descent (PGD) method has shown to be effective in recovering compressed signals described in a data-driven way by a generative model, i.e., a generator which has learned the data distribution. Furt…

compressed sensingGenerative Adversarial Network