论文标题
瓢虫：Quasi-Monte Carlo采样，用于深层隐式场的3D重建与对称性
Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry
论文作者
论文摘要
深层的字段回归方法对来自单视图像的3D重建有效。但是，不同的抽样模式对重建质量的影响并不理解。在这项工作中，我们首先研究了点集差异对网络培训的影响。基于最远的点采样算法，我们提出了一种抽样方案，从理论上讲，该方案可以鼓励更好的概括性能，并导致基于SGD的优化算法的快速收敛。其次，基于对象的反射对称性，我们提出了一种特征融合方法，该方法由于自我观察而导致的问题，这使得很难使用本地图像特征。我们提出的系统瓢虫能够从单个输入图像创建高质量的3D对象重建。我们在大规模的3D数据集（Shapenet）上评估瓢虫，在倒角距离，地球搬运工的距离和联合（IOU）的相交方面表现出了高度竞争的结果。
Deep implicit field regression methods are effective for 3D reconstruction from single-view images. However, the impact of different sampling patterns on the reconstruction quality is not well-understood. In this work, we first study the effect of point set discrepancy on the network training. Based on Farthest Point Sampling algorithm, we propose a sampling scheme that theoretically encourages better generalization performance, and results in fast convergence for SGD-based optimization algorithms. Secondly, based on the reflective symmetry of an object, we propose a feature fusion method that alleviates issues due to self-occlusions which makes it difficult to utilize local image features. Our proposed system Ladybird is able to create high quality 3D object reconstructions from a single input image. We evaluate Ladybird on a large scale 3D dataset (ShapeNet) demonstrating highly competitive results in terms of Chamfer distance, Earth Mover's distance and Intersection Over Union (IoU).
