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 1808.07413cs.CV
收藏

通过幻觉操纵自然场景的属性

Manipulating Attributes of Natural Scenes via Hallucination

Hacettepe University(哈塞特佩大学);Iskenderun Technical University(伊斯肯德伦理工大学);University of Tübingen(图宾根大学)

Levent Karacan, Zeynep Akata, Aykut Erdem, Erkut Erdem

摘要:

在这项研究中,我们探索建立一个两阶段的框架,使用户能够直接操纵高层次的属性的自然场景。我们的方法的关键是一个深度生成网络,它可以使场景的图像产生幻觉,就好像它们是在不同的季节(例如在冬季),天气条件(例如在阴天)或一天中的时间(例如在日落时)拍摄的。一旦场景用给定的属性产生幻觉,相应的外观就会被转移到输入图像,同时保持语义细节不变,从而给出照片般逼真的操作结果。由于所提出的框架使场景看起来像幻觉,因此它不需要任何参考样式图像,因为大多数外观或样式转移方法中通常使用该参考样式图像。此外,它允许根据单个模型中的各种瞬态属性集同时操纵给定场景,从而消除了每个翻译任务训练多个网络的需要。我们全面的定性和定量结果证明了我们的方法对竞争方法的有效性。

英文摘要:

In this study, we explore building a two-stage framework for enabling users to directly manipulate high-level attributes of a natural scene. The key to our approach is a deep generative network which can hallucinate images of a scene as if they were taken at a different season (e.g. during winter), weather condition (e.g. in a cloudy day) or time of the day (e.g. at sunset). Once the scene is hallucinated with the given attributes, the corresponding look is then transferred to the input image while preserving the semantic details intact, giving a photo-realistic manipulation result. As the proposed framework hallucinates what the scene will look like, it does not require any reference style image as commonly utilized in most of the appearance or style transfer approaches. Moreover, it allows to simultaneously manipulate a given scene according to a diverse set of transient attributes within a single model, eliminating the need of training multiple networks per each translation task. Our comprehensive set of qualitative and quantitative results demonstrate the effectiveness of our approach against the competing methods.

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。

↑