State-of-the-art learning-based monocular 3D reconstruction methods learn
priors over object categories on the training set, and as a result struggle to
achieve reasonable generalization to object categories unseen during training.
In this paper we study the inductive biases encoded in the model architecture
that impact the generalization of learning-based 3D reconstruction methods. We
find that 3 inductive biases impact performance: the spatial extent of the
encoder, the use of the underlying geometry of the scene to describe point
features, and the mechanism to aggregate information from multiple views.
Additionally, we propose mechanisms to enforce those inductive biases: a point
representation that is aware of camera position, and a variance cost to
aggregate information across views. Our model achieves state-of-the-art results
on the standard ShapeNet 3D reconstruction benchmark in various settings.

本文研究了学习基础的 3D 重建方法在体现经验偏好时的架构问题，发现编码器空间范围、场景几何特征描述和多视图信息聚合机制对性能的影响，并提出相应的机制以增强对这些经验偏好的表达。在 ShapeNet 基准测试中，我们的模型在各种设置下均实现了最先进的成果。

基于学习的三维重建的泛化

On the generalization of learning-based 3D reconstruction

Several popular approaches to 3D vision tasks process multiple views of the
input independently with deep neural networks pre-trained on natural images,
achieving view permutation invariance through a single round of pooling over
all views. We argue that this operation discards important information and
leads to subpar global descriptors. In this paper, we propose a group
convolutional approach to multiple view aggregation where convolutions are
performed over a discrete subgroup of the rotation group, enabling, thus, joint
reasoning over all views in an equivariant (instead of invariant) fashion, up
to the very last layer. We further develop this idea to operate on smaller
discrete homogeneous spaces of the rotation group, where a polar view
representation is used to maintain equivariance with only a fraction of the
number of input views. We set the new state of the art in several large scale
3D shape retrieval tasks, and show additional applications to panoramic scene
classification.

本文提出了一种基于群卷积的多视图融合方法，实现对所有视图的联合推理，并通过对旋转群的离散子群进行卷积来维持等变性，从而在多个大规模的 3D 形状检索任务中取得了新的最高水平，并且在全景场景分类方面也有额外的应用。