DeepAI AI Chat
Log In Sign Up

Nested Scale Editing for Conditional Image Synthesis

by   Lingzhi Zhang, et al.

We propose an image synthesis approach that provides stratified navigation in the latent code space. With a tiny amount of partial or very low-resolution image, our approach can consistently out-perform state-of-the-art counterparts in terms of generating the closest sampled image to the ground truth. We achieve this through scale-independent editing while expanding scale-specific diversity. Scale-independence is achieved with a nested scale disentanglement loss. Scale-specific diversity is created by incorporating a progressive diversification constraint. We introduce semantic persistency across the scales by sharing common latent codes. Together they provide better control of the image synthesis process. We evaluate the effectiveness of our proposed approach through various tasks, including image outpainting, image superresolution, and cross-domain image translation.


page 1

page 5

page 6

page 7

page 15

page 16

page 17

page 18


Variational Bayesian Framework for Advanced Image Generation with Domain-Related Variables

Deep generative models (DGMs) and their conditional counterparts provide...

FlexIT: Towards Flexible Semantic Image Translation

Deep generative models, like GANs, have considerably improved the state ...

Diversifying Semantic Image Synthesis and Editing via Class- and Layer-wise VAEs

Semantic image synthesis is a process for generating photorealistic imag...

CAFLOW: Conditional Autoregressive Flows

We introduce CAFLOW, a new diverse image-to-image translation model that...

LSC-GAN: Latent Style Code Modeling for Continuous Image-to-image Translation

Image-to-image (I2I) translation is usually carried out among discrete d...

StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN

Recently, StyleGAN has enabled various image manipulation and editing ta...