Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
arXiv:1912.12215
Abstract
In this paper, we address the task of semantic-guided scene generation. One open challenge in scene generation is the difficulty of the generation of small objects and detailed local texture, which has been widely observed in global image-level generation methods. To tackle this issue, in this work we consider learning the scene generation in a local context, and correspondingly design a local class-specific generative network with semantic maps as a guidance, which separately constructs and learns sub-generators concentrating on the generation of different classes, and is able to provide more scene details. To learn more discriminative class-specific feature representations for the local generation, a novel classification module is also proposed. To combine the advantage of both the global image-level and the local class-specific generation, a joint generation network is designed with an attention fusion module and a dual-discriminator structure embedded. Extensive experiments on two scene image generation tasks show superior generation performance of the proposed model. The state-of-the-art results are established by large margins on both tasks and on challenging public benchmarks. The source code and trained models are available at https://github.com/Ha0Tang/LGGAN.
arXiv commentAccepted to CVPR 2020, camera ready (10 pages) + supplementary (18 pages)
References in corpus (16)
- Conditional Generative Adversarial Nets
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Spectral Normalization for Generative Adversarial Networks
- Self-Attention Generative Adversarial Networks
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Semi-Supervised Learning with Generative Adversarial Networks
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
- Unsupervised Attention-guided Image to Image Translation
- Learning What and Where to Draw
- GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
- Controllable Text-to-Image Generation
- Cross-view image synthesis using geometry-guided conditional GANs
- Progressive Pose Attention Transfer for Person Image Generation
- AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks
- InGAN: Capturing and Remapping the "DNA" of a Natural Image