论文标题
学会生成传达几何图形和语义的线图
Learning to generate line drawings that convey geometry and semantics
论文作者
论文摘要
本文提出了一种从照片中创建线条图的未配对方法。当前方法通常依靠高质量的配对数据集来生成线条图。但是，由于属于特定域或收集的数据量，这些数据集通常由于图纸的主题而存在局限性。尽管无监督的图像到图像翻译的最新工作已经显示出很大的进步，但最新的方法仍然难以生成引人注目的线条图。我们观察到线图是场景信息的编码，并试图传达3D形状和语义含义。我们将这些观察结果构建为一组目标，并训练图像翻译以将照片映射到线图中。我们引入了几何损失，该几何损失可以从线图的图像特征中预测深度信息，以及与线图的剪辑特征与其相应照片相匹配的语义损失。我们的方法优于最先进的未配对的图像翻译和线绘图生成的方法，这些方法是从任意照片创建线条图的。有关代码和演示，请访问我们的网页carolineec.github.io/informative_drawings
This paper presents an unpaired method for creating line drawings from photographs. Current methods often rely on high quality paired datasets to generate line drawings. However, these datasets often have limitations due to the subjects of the drawings belonging to a specific domain, or in the amount of data collected. Although recent work in unsupervised image-to-image translation has shown much progress, the latest methods still struggle to generate compelling line drawings. We observe that line drawings are encodings of scene information and seek to convey 3D shape and semantic meaning. We build these observations into a set of objectives and train an image translation to map photographs into line drawings. We introduce a geometry loss which predicts depth information from the image features of a line drawing, and a semantic loss which matches the CLIP features of a line drawing with its corresponding photograph. Our approach outperforms state-of-the-art unpaired image translation and line drawing generation methods on creating line drawings from arbitrary photographs. For code and demo visit our webpage carolineec.github.io/informative_drawings
