• Corpus ID: 244909086

DRAN: Detailed Region-Adaptive Normalization for Conditional Image Synthesis

  title={DRAN: Detailed Region-Adaptive Normalization for Conditional Image Synthesis},
  author={Yueming Lyu and P. Chen and Jingna Sun and Xu Wang and Jing Dong and Tieniu Tan},
In recent years, conditional image synthesis has attracted growing attention due to its controllability in the image generation process. Although recent works have achieved realistic results, most of them fail to handle finegrained styles with subtle details. To address this problem, a novel normalization module, named DRAN, is proposed. It learns fine-grained style representation, while maintaining the robustness to general styles. Specifically, we first introduce a multi-level structure… 



SEAN: Image Synthesis With Semantic Region-Adaptive Normalization

We propose semantic region-adaptive normalization (SEAN), a simple but effective building block for Generative Adversarial Networks conditioned on segmentation masks that describe the semantic

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

A new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs) is presented, which significantly outperforms existing methods, advancing both the quality and the resolution of deep image synthesis and editing.

Learning Semantic Person Image Generation by Region-Adaptive Normalization

  • Zheng LvXiaoming Li W. Zuo
  • Computer Science
    2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2021
This work proposes a new two-stage framework to handle the pose and appearance translation and suggests a new person image generation method by incorporating the region-adaptive normalization, in which it takes the per-region styles to guide the target appearance generation.

Region-aware Adaptive Instance Normalization for Image Harmonization

This paper proposes a simple yet effective Region-aware Adaptive Instance Normalization (RAIN) module, which explicitly formulates the visual style from the background and adaptively applies them to the foreground.

Controllable Person Image Synthesis With Attribute-Decomposed GAN

The Attribute-Decomposed GAN is introduced, a novel generative model for controllable person image synthesis, which can produce realistic person images with desired human attributes provided in various source inputs and its superiority over the state of the art in pose transfer and its effectiveness in the brand-new task of component attribute transfer.

StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks

This paper proposes Stacked Generative Adversarial Networks (StackGAN) to generate 256 photo-realistic images conditioned on text descriptions and introduces a novel Conditioning Augmentation technique that encourages smoothness in the latent conditioning manifold.

Semantic Image Synthesis With Spatially-Adaptive Normalization

S spatially-adaptive normalization is proposed, a simple but effective layer for synthesizing photorealistic images given an input semantic layout that allows users to easily control the style and content of image synthesis results as well as create multi-modal results.

Perceptual Losses for Real-Time Style Transfer and Super-Resolution

This work considers image transformation problems, and proposes the use of perceptual loss functions for training feed-forward networks for image transformation tasks, and shows results on image style transfer, where aFeed-forward network is trained to solve the optimization problem proposed by Gatys et al. in real-time.

Large Scale GAN Training for High Fidelity Natural Image Synthesis

It is found that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input.

Semantically Multi-Modal Image Synthesis

A novel Group Decreasing Network (GroupDNet) is proposed that leverages group convolution in the generator and progressively decreases the group numbers of the convolutions in the decoder, which is armed with much more controllability on translating semantic labels to natural images and has plausible high-quality yields for datasets with many classes.