Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation
This work addresses the problem of improving scene generation quality for computer vision applications, representing an incremental advancement by combining global and local generation methods.
The paper tackles the challenge of generating small objects and detailed local textures in semantic-guided scene generation by introducing a local class-specific generative network and a joint generation network with attention fusion and dual discriminators. It achieves state-of-the-art results with large margins on two scene image generation tasks and public benchmarks.
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.