Learning Pose-invariant 3D Object Reconstruction from Single-view Images
Learning Pose-invariant 3D Object Reconstruction from Single-view Images
复制标题
DOI：
10.1016/j.neucom.2020.10.089
复制
发表时间：
2020-04
期刊：
影响因子：
6
通讯作者：
Bo Peng;Wei Wang-;Jing Dong;T. Tan
中科院分区：
文献类型：
--
作者：
Bo Peng;Wei Wang-;Jing Dong;T. Tan
学习使用2D图像重建3D形状是一个活跃的研究课题，其优点是不需要昂贵的3D数据。然而，在这个方向上的大多数工作需要多视图图像为每个对象实例作为训练监督，这往往不适用于实践。在本文中，我们放松了常见的多视图假设，并探索了一个更具挑战性但更现实的设置，仅从单视图图像学习3D形状。主要的困难在于单视图图像提供的约束不足，这导致了学习形状空间中的姿态纠缠问题。结果，重构的形状沿着输入姿态变化并且具有差的精度。我们通过采取一种新的域自适应的角度来解决这个问题，并提出了一种有效的对抗域混淆方法来学习姿态解纠缠的紧凑形状空间。单视图重建实验表明，该方法能有效解决姿态纠缠问题，重建精度与现有方法相当，且效率较高。
Learning to reconstruct 3D shapes using 2D images is an active research topic, with benefits of not requiring expensive 3D data. However, most work in this direction requires multi-view images for each object instance as training supervision, which oftentimes does not apply in practice. In this paper, we relax the common multi-view assumption and explore a more challenging yet more realistic setup of learning 3D shape from only single-view images. The major difficulty lies in insufficient constraints that can be provided by single view images, which leads to the problem of pose entanglement in learned shape space. As a result, reconstructed shapes vary along input pose and have poor accuracy. We address this problem by taking a novel domain adaptation perspective, and propose an effective adversarial domain confusion method to learn pose-disentangled compact shape space. Experiments on single-view reconstruction show effectiveness in solving pose entanglement, and the proposed method achieves on-par reconstruction accuracy with state-of-the-art with higher efficiency.