arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.00640cs.CV
收藏

感知感知空间融合的真实感场景布局生成

Relationship-Aware Spatial Perception Fusion for Realistic Scene Layout Generation

Hongdong Zheng, Yalong Bai, Wei Zhang, Tao Mei

摘要:

生成对抗网络(GANs)的重大进展使得基于自然语言描述为单个对象生成令人惊讶的逼真图像成为可能。然而,由于场景布局生成严重地受到多样性对象缩放和空间位置的影响,具有显式交互的多个实体的图像的受控生成仍然难以实现。在本文中,我们提出了一个新的框架,从文本场景图生成逼真的图像布局。在该框架中,空间约束模块的设计,以适应合理的缩放和空间布局的对象对之间的关系,同时考虑到它们之间的。此外,上下文融合模块被引入融合成对的空间信息的场景图中的对象依赖。通过使用这两个模块,我们提出的框架往往会产生更多的常识布局,这是真实感图像生成的帮助。实验结果,包括定量结果,定性结果和用户研究两个不同的场景图数据集证明我们提出的框架的能力,以产生复杂的和逻辑布局的多个对象从场景图。

英文摘要:

The significant progress on Generative Adversarial Networks (GANs) have made it possible to generate surprisingly realistic images for single object based on natural language descriptions. However, controlled generation of images for multiple entities with explicit interactions is still difficult to achieve due to the scene layout generation heavily suffer from the diversity object scaling and spatial locations. In this paper, we proposed a novel framework for generating realistic image layout from textual scene graphs. In our framework, a spatial constraint module is designed to fit reasonable scaling and spatial layout of object pairs with considering relationship between them. Moreover, a contextual fusion module is introduced for fusing pair-wise spatial information in terms of object dependency in scene graph. By using these two modules, our proposed framework tends to generate more commonsense layout which is helpful for realistic image generation. Experimental results including quantitative results, qualitative results and user studies on two different scene graph datasets demonstrate our proposed framework's ability to generate complex and logical layout with multiple objects from scene graph.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑