SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
复制标题
DOI：
--
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Chen-Hsuan Lin;Chaoyang Wang;S. Lucey
中科院分区：
文献类型：
--
作者：
Chen-Hsuan Lin;Chaoyang Wang;S. Lucey
从单个图像重建密集的3D对象最近取得了显着的进步，但是由于创建成对图像-形状数据集的过程非常繁琐，因此使用地面真实3D形状来监督神经网络是不切实际的。最近的努力已经转向学习3D重建，而无需从具有注释的2D轮廓的RGB图像进行3D监督，从而大大降低了注释的成本和工作量。然而，这些技术仍然不切实际，因为它们仍然需要在训练期间对同一对象实例进行多视图注释。因此，到目前为止，大多数实验工作仅限于合成数据集。在本文中，我们解决了这个问题，并提出了SDF-SRN，这种方法在训练时只需要对象的单个视图，为现实世界的场景提供了更大的实用性。SDF-SRN学习隐式3D形状表示来处理数据集中可能存在的任意形状拓扑。为此，我们推导出一种新的微分绘制公式，用于从2D轮廓学习符号距离函数（SDF）。我们的方法在合成和真实世界数据集上具有挑战性的单视图监督设置下的性能优于现有技术。
Dense 3D object reconstruction from a single image has recently witnessed remarkable advances, but supervising neural networks with ground-truth 3D shapes is impractical due to the laborious process of creating paired image-shape datasets. Recent efforts have turned to learning 3D reconstruction without 3D supervision from RGB images with annotated 2D silhouettes, dramatically reducing the cost and effort of annotation. These techniques, however, remain impractical as they still require multi-view annotations of the same object instance during training. As a result, most experimental efforts to date have been limited to synthetic datasets. In this paper, we address this issue and propose SDF-SRN, an approach that requires only a single view of objects at training time, offering greater utility for real-world scenarios. SDF-SRN learns implicit 3D shape representations to handle arbitrary shape topologies that may exist in the datasets. To this end, we derive a novel differentiable rendering formulation for learning signed distance functions (SDF) from 2D silhouettes. Our method outperforms the state of the art under challenging single-view supervision settings on both synthetic and real-world datasets.