Reconstructing 3D shapes from single-view images has been a long-standing research problem. In this paper, we present DISN, a Deep Implicit Surface Network which can generate a high-quality detail-rich 3D mesh from an 2D image by predicting the underlying signed distance fields. In addition to utilizing global image features, DISN predicts the projected location for each 3D point on the 2D image, and extracts local features from the image feature maps. Combining global and local features significantly improves the accuracy of the signed distance field prediction, especially for the detail-rich areas. To the best of our knowledge, DISN is the first method that constantly captures details such as holes and thin structures present in 3D shapes from single-view images. DISN achieves the state-of-the-art single-view reconstruction performance on a variety of shape categories reconstructed from both synthetic and real images. Code is available at https://github.com/xharlie/DISN The supplementary can be found at https://xharlie.github.io/images/neurips_2019_supp.pdf

翻译：从单视图像中重建 3D 形状是一个长期的研究问题。 在本文中, 我们介绍DISN, 是一个深隐性表面网络, 通过预测基本签名的距离字段, 可以从 2D 图像中产生高质量的详细内容丰富的 3D 网格。 除了使用全球图像外, DISN 预测 2D 图像上每个 3D 点的预测位置, 并从图像地貌地图中提取本地特征 。 将全球和本地地貌结合起来, 大大提高了所签署的远域预测的准确性, 特别是细节丰富的区域的准确性 。 据我们所知, DISSN 是第一个不断捕捉细节的方法, 例如从单视图像中以 3D 形状显示的洞和薄结构 。 DISN 在从合成图像和真实图像中重建的形状类别上都达到最先进的单视重建性能 。 代码可在 https://github.com/xharlie/DISN 上查阅的远域预测 。 补充可在 https://xharlie.githubio/images/neutrips_20ps_p19_ps.