MsCGAN: Multi-scale Conditional Generative Adversarial Networks for Person Image Generation
To synthesize high-quality person images with arbitrary poses is challenging. In this paper, we propose a novel Multi-scale Conditional Generative Adversarial Networks (MsCGAN), aiming to convert the input conditional person image to a synthetic image of any given target pose, whose appearance and the texture are consistent with the input image. MsCGAN is a multi-scale adversarial network consisting of two generators and two discriminators. One generator transforms the conditional person image into a coarse image of the target pose globally, and the other is to enhance the detailed quality of the synthetic person image through a local reinforcement network. The outputs of the two generators are then merged into a synthetic, discriminant and high-resolution image. On the other hand, the synthetic image is downsampled to multiple resolutions as the input to multi-scale discriminator networks. The proposed multi-scale generators and discriminators handling different levels of visual features can benefit to synthesizing high-resolution person images with realistic appearance and texture. Experiments are conducted on the Market-1501 and DeepFashion datasets to evaluate the proposed model, and both qualitative and quantitative results demonstrate the superior performance of the proposed MsCGAN.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationSimilar Papers 제목 키워드 기반
LinesToFacePhoto: Face Photo Generation from Lines with Conditional Self-Attention Generative Adversarial Network
In this paper, we explore the task of generating photo-realistic face images from lines. Previous methods based on conditional generative adversarial networks (cGANs) have shown their power to generate visually plausible…
Generative Adversarial NetworkStackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
Although Generative Adversarial Networks (GANs) have shown remarkable success in various tasks, they still face challenges in generating high quality images. In this paper, we propose Stacked Generative Adversarial Netwo…
Generative Adversarial NetworkImage GenerationText-to-Image GenerationLarge Scale Image Completion via Co-Modulated Generative Adversarial Networks
Numerous task-specific variants of conditional generative adversarial networks have been developed for image completion. Yet, a serious limitation remains that all existing algorithms tend to fail when handling large-sca…
DiversityImage InpaintingImage-to-Image TranslationTranslationDiversity Augmented Conditional Generative Adversarial Network for Enhanced Multimodal Image-to-Image Translation
Conditional generative adversarial networks (cGANs) play an important role in multimodal image-to-image translation. We propose Diversity Augmented conditional Generative Adversarial Network (DivAugGAN), a highly effecti…
DiversityGenerative Adversarial NetworkImage-to-Image TranslationTranslationLabel-Noise Robust Generative Adversarial Networks
Generative adversarial networks (GANs) are a framework that learns a generative distribution through adversarial training. Recently, their class-conditional extensions (e.g., conditional GAN (cGAN) and auxiliary classifi…
Robust classification