Spatially Constrained Generative Adversarial Networks for Conditional Image Generation

05/07/2019
by   Songyao Jiang, et al.
0

Image generation has raised tremendous attention in both academic and industrial areas, especially for the conditional and target-oriented image generation, such as criminal portrait and fashion design. Although the current studies have achieved preliminary results along this direction, they always focus on class labels as the condition where spatial contents are randomly generated from latent vectors. Edge details are usually blurred since spatial information is difficult to preserve. In light of this, we propose a novel Spatially Constrained Generative Adversarial Network (SCGAN), which decouples the spatial constraints from the latent vector and makes these constraints feasible as additional controllable signals. To enhance the spatial controllability, a generator network is specially designed to take a semantic segmentation, a latent vector and an attribute-level label as inputs step by step. Besides, a segmentor network is constructed to impose spatial constraints on the generator. Experimentally, we provide both visual and quantitative results on CelebA and DeepFashion datasets, and demonstrate that the proposed SCGAN is very effective in controlling the spatial contents as well as generating high-quality images.

READ FULL TEXT

page 4

page 5

page 10

page 12

page 13

page 14

page 16

research
03/05/2020

Image Generation from Freehand Scene Sketches

We introduce the first method for automatic image generation from scene-...
research
09/16/2019

Controllable Text-to-Image Generation

In this paper, we propose a novel controllable text-to-image generative ...
research
09/22/2019

Variational Conditional GAN for Fine-grained Controllable Image Generation

In this paper, we propose a novel variational generator framework for co...
research
11/05/2020

DTGAN: Dual Attention Generative Adversarial Networks for Text-to-Image Generation

Most existing text-to-image generation methods adopt a multi-stage modul...
research
03/25/2023

Spatial Latent Representations in Generative Adversarial Networks for Image Generation

In the majority of GAN architectures, the latent space is defined as a s...
research
09/04/2020

TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator

Advances in technology have led to the development of methods that can c...
research
08/02/2019

Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation

In this work, we propose a novel Cycle In Cycle Generative Adversarial N...

Please sign up or login with your details

Forgot password? Click here to reset