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 1909.08313cs.CV
收藏

无监督的草图到照片合成

Unsupervised Sketch-to-Photo Synthesis

UC Berkeley(加州大学伯克利分校);ICSI(国际计算机科学研究所);Peking University(北京大学);Beihang University(北京航空航天大学)

Runtao Liu, Qian Yu, Stella Yu

摘要:

人类可以想象一张真实的照片,给出一张手绘草图,不仅空间上不精确,几何上扭曲,而且没有颜色和视觉细节。我们首次研究了无监督的草图到照片合成,从未配对的草图照片数据中学习,其中草图的目标照片在训练过程中是未知的。现有的作品只处理风格变化或空间变形,从边缘对齐的线条画合成照片或在同一模态中转换形状,例如,彩色图像。我们的关键见解是将无监督的草图到照片合成分解为两个阶段的转换任务:首先从草图到灰度照片的形状转换,然后从灰度到彩色照片的内容丰富。我们还结合了一个自我监督的去噪目标和一个注意力模块来处理抽象和风格变化,这些变化是草图固有的和特定的。我们的合成是草图忠实和照片逼真,使草图为基础的图像检索在实践中。一个令人兴奋的必然产品是一个通用的和有前途的草图生成器,捕捉人类的视觉感知超越边缘地图的照片。

英文摘要:

Humans can envision a realistic photo given a free-hand sketch that is not only spatially imprecise and geometrically distorted but also without colors and visual details. We study unsupervised sketch-to-photo synthesis for the first time, learning from unpaired sketch-photo data where the target photo for a sketch is unknown during training. Existing works only deal with style change or spatial deformation alone, synthesizing photos from edge-aligned line drawings or transforming shapes within the same modality, e.g., color images. Our key insight is to decompose unsupervised sketch-to-photo synthesis into a two-stage translation task: First shape translation from sketches to grayscale photos and then content enrichment from grayscale to color photos. We also incorporate a self-supervised denoising objective and an attention module to handle abstraction and style variations that are inherent and specific to sketches. Our synthesis is sketch-faithful and photo-realistic to enable sketch-based image retrieval in practice. An exciting corollary product is a universal and promising sketch generator that captures human visual perception beyond the edge map of a photo.

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。

↑