We propose a novel method for 3D object reconstruction from a sparse set of
views captured from a 360-degree calibrated camera rig. We represent the object
surface through a hybrid model that uses both an MLP-based neural
representation and a triangle mesh. A key contribution in our work is a novel
object-centric sampling scheme of the neural representation, where rays are
shared among all views. This efficiently concentrates and reduces the number of
samples used to update the neural model at each iteration. This sampling scheme
relies on the mesh representation to ensure also that samples are
well-distributed along its normals. The rendering is then performed efficiently
by a differentiable renderer. We demonstrate that this sampling scheme results
in a more effective training of the neural representation, does not require the
additional supervision of segmentation masks, yields state of the art 3D
reconstructions, and works with sparse views on the Google's Scanned Objects,
Tank and Temples and MVMC Car datasets.

我们提出了一种从由 360 度校准相机组拍摄的一组稀疏视图中重建 3D 物体的新方法。我们通过混合模型，使用基于 MLP 的神经表示和三角形网格，表示对象表面。我们工作的一个关键贡献是一种新颖的以对象为中心的神经表示采样方案，其中的光线在所有视图之间共享。这种采样方案通过网格表示确保样本沿法线方向分布均匀。然后，通过可微分的渲染器高效地进行渲染。我们证明了这种采样方案能更有效地训练神经表示，不需要额外的分割蒙版的监督，能获得最先进的 3D 重建结果，并且适用于 Google 的 Scanned Objects、Tank and Temples 和 MVMC Car 数据集的稀疏视图。