paper-with-me

홈 › Papers

Learning to navigate image manifolds induced by generative adversarial networks for unsupervised video generation

2019-01-23 · Isabela Albuquerque, João Monteiro, Tiago H. Falk

In this work, we introduce a two-step framework for generative modeling of temporal data. Specifically, the generative adversarial networks (GANs) setting is employed to generate synthetic scenes of moving objects. To do so, we propose a two-step training scheme within which: a generator of static frames is trained first. Afterwards, a recurrent model is trained with the goal of providing a sequence of inputs to the previously trained frames generator, thus yielding scenes which look natural. The adversarial setting is employed in both training steps. However, with the aim of avoiding known training instabilities in GANs, a multiple discriminator approach is used to train both models. Results in the studied video dataset indicate that, by employing such an approach, the recurrent part is able to learn how to coherently navigate the image manifold induced by the frames generator, thus yielding more natural-looking scenes.

📄 PDF Abstract BibTeX arXiv:1901.11384

Code (1)

belaalb/frameGAN 공식 구현 pytorch

Tasks

NavigateVideo Generation

Similar Papers 제목 키워드 기반

Manifold Learning and Alignment with Generative Adversarial Networks

2019-09-25 · Jiseob Kim, Seungjae Jung, Hyundo Lee, Byoung-Tak Zhang

We present a generative adversarial network (GAN) that conducts manifold learning and alignment (MLA): A task to learn the multi-manifold structure underlying data and to align those manifolds without any correspondence …

DisentanglementGenerative Adversarial Network

Quantifying Manifolds: Do the manifolds learned by Generative Adversarial Networks converge to the real data manifold

2024-03-08 · Anupam Chaudhuri, Anj Simmons, Mohamed Abdelrazek

This paper presents our experiments to quantify the manifolds learned by ML models (in our experiment, we use a GAN model) as they train. We compare the manifolds learned at each epoch to the real manifolds representing …

MMGAN: Manifold Matching Generative Adversarial Network

2017-07-26 · Noseong Park, Ankesh Anand, Joel Ruben Antony Moniz, Kookjin Lee 외

It is well-known that GANs are difficult to train, and several different techniques have been proposed in order to stabilize their training. In this paper, we propose a novel training method called manifold-matching, and…

Generative Adversarial Network

Manifold-valued Image Generation with Wasserstein Generative Adversarial Nets

2017-12-05 · Zhiwu Huang, Jiqing Wu, Luc van Gool

Generative modeling over natural images is one of the most fundamental machine learning problems. However, few modern generative models, including Wasserstein Generative Adversarial Nets (WGANs), are studied on manifold-…

Image Generation

Mask-Guided Discovery of Semantic Manifolds in Generative Models

2021-05-15 · Mengyu Yang, David Rokeby, Xavier Snelgrove

Advances in the realm of Generative Adversarial Networks (GANs) have led to architectures capable of producing amazingly realistic images such as StyleGAN2, which, when trained on the FFHQ dataset, generates images of hu…

Disentanglement