论文标题
通过无监督域的适应在隐式模型上从单个图像中重建雕塑的3D重建
3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models
论文作者
论文摘要
在虚拟现实（VR）博物馆中获得相当于雕塑的虚拟等效物可能是劳动密集型的，有时甚至是不可行的。基于深度学习的3D重建方法使我们能够从2D观察结果中恢复3D形状，其中基于单视图的方法可以减少对人为干预的需求和专门设备，以获取VR博物馆的3D雕塑。但是，尝试使用经过精心研究的人类重建方法时存在两个挑战：数据可用性有限和域转移。考虑到雕塑通常与人类有关，我们提出了无监督的3D域适应方法，用于调整从源（现实世界人类）到目标（雕塑）域的单视3D 3D隐式重建模型。我们已经将生成的形状与其他方法进行了比较，并进行了消融研究以及用户研究，以证明我们适应方法的有效性。我们还将结果部署到VR应用程序中。
Acquiring the virtual equivalent of exhibits, such as sculptures, in virtual reality (VR) museums, can be labour-intensive and sometimes infeasible. Deep learning based 3D reconstruction approaches allow us to recover 3D shapes from 2D observations, among which single-view-based approaches can reduce the need for human intervention and specialised equipment in acquiring 3D sculptures for VR museums. However, there exist two challenges when attempting to use the well-researched human reconstruction methods: limited data availability and domain shift. Considering sculptures are usually related to humans, we propose our unsupervised 3D domain adaptation method for adapting a single-view 3D implicit reconstruction model from the source (real-world humans) to the target (sculptures) domain. We have compared the generated shapes with other methods and conducted ablation studies as well as a user study to demonstrate the effectiveness of our adaptation method. We also deploy our results in a VR application.
