Search Results for author: Jiapeng Zhu

Found 6 papers, 4 papers with code

Low-Rank Subspaces in GANs

1 code implementation8 Jun 2021 Jiapeng Zhu, Ruili Feng, Yujun Shen, Deli Zhao, ZhengJun Zha, Jingren Zhou, Qifeng Chen

Concretely, given an arbitrary image and a region of interest (e. g., eyes of face images), we manage to relate the latent space to the image region with the Jacobian matrix and then use low-rank factorization to discover steerable latent subspaces.

Generative Hierarchical Features from Synthesizing Images

1 code implementation CVPR 2021 Yinghao Xu, Yujun Shen, Jiapeng Zhu, Ceyuan Yang, Bolei Zhou

Generative Adversarial Networks (GANs) have recently advanced image synthesis by learning the underlying distribution of the observed data.

Face Verification Image Classification +2

In-Domain GAN Inversion for Real Image Editing

3 code implementations ECCV 2020 Jiapeng Zhu, Yujun Shen, Deli Zhao, Bolei Zhou

A common practice of feeding a real image to a trained GAN generator is to invert it back to a latent code.

GAN inversion Image Interpolation +1

Latent Variables on Spheres for Autoencoders in High Dimensions

no code implementations21 Dec 2019 Deli Zhao, Jiapeng Zhu, Bo Zhang

Variational Auto-Encoder (VAE) has been widely applied as a fundamental generative model in machine learning.

Curriculum Learning for Deep Generative Models with Clustering

no code implementations27 Jun 2019 Deli Zhao, Jiapeng Zhu, Zhenfang Guo, Bo Zhang

The experiments on cat and human-face data validate that our algorithm is able to learn the optimal generative models (e. g. ProGAN) with respect to specified quality metrics for noisy data.

Curriculum Learning

Disentangled Inference for GANs with Latently Invertible Autoencoder

3 code implementations19 Jun 2019 Jiapeng Zhu, Deli Zhao, Bo Zhang, Bolei Zhou

In this paper, we show that the entanglement of the latent space for the VAE/GAN framework poses the main challenge for encoder learning.

Cannot find the paper you are looking for? You can Submit a new open access paper.