论文标题
D $^2 $ im-net：学习细节从单个图像中删除隐式字段
D$^2$IM-Net: Learning Detail Disentangled Implicit Fields from Single Images
论文作者
论文摘要
我们提出了第一个单视3D重建网络，该网络旨在从涵盖拓扑形状结构和表面特征的输入图像中恢复几何细节。我们的关键想法是训练网络，以学习一个细节，该细节由两个函数组成，其中一个代表粗3D形状的隐性字段，另一个代表详细信息。在给定输入图像的情况下，我们的网络创建的D $^2 $ im-net将其编码为全球和本地功能，这些功能分别被馈送到两个解码器中。基本解码器使用全局功能重建一个粗隐式字段，而细节解码器从本地特征，两个位移映射从捕获的对象的正面和后侧定义。最终的3D重建是基本形状和位移图之间的融合，三个损失通过新颖的拉普拉斯术语实施了粗糙形状，整体结构和表面细节的恢复。
We present the first single-view 3D reconstruction network aimed at recovering geometric details from an input image which encompass both topological shape structures and surface features. Our key idea is to train the network to learn a detail disentangled reconstruction consisting of two functions, one implicit field representing the coarse 3D shape and the other capturing the details. Given an input image, our network, coined D$^2$IM-Net, encodes it into global and local features which are respectively fed into two decoders. The base decoder uses the global features to reconstruct a coarse implicit field, while the detail decoder reconstructs, from the local features, two displacement maps, defined over the front and back sides of the captured object. The final 3D reconstruction is a fusion between the base shape and the displacement maps, with three losses enforcing the recovery of coarse shape, overall structure, and surface details via a novel Laplacian term.
