Despite recent advancements in deep neural networks for point cloud
recognition, real-world safety-critical applications present challenges due to
unavoidable data corruption. Current models often fall short in generalizing to
unforeseen distribution shifts. In this study, we harness the inherent set
property of point cloud data to introduce a novel critical subset
identification (CSI) method, aiming to bolster recognition robustness in the
face of data corruption. Our CSI framework integrates two pivotal components:
density-aware sampling (DAS) and self-entropy minimization (SEM), which cater
to static and dynamic CSI, respectively. DAS ensures efficient robust anchor
point sampling by factoring in local density, while SEM is employed during
training to accentuate the most salient point-to-point attention. Evaluations
reveal that our CSI approach yields error rates of 18.4\% and 16.3\% on
ModelNet40-C and PointCloud-C, respectively, marking a notable improvement over
state-of-the-art methods by margins of 5.2\% and 4.2\% on the respective
benchmarks. Code is available at
\href{https://github.com/masterwu2115/CSI/tree/main}{this https URL}

该研究针对点云数据的不可避免的数据损坏问题，提出了基于关键子集识别（CSI）方法，通过密度感知采样（DAS）和自熵最小化（SEM）两个关键组件来提高点云识别的鲁棒性。实验证明，该方法在 ModelNet40-C 和 PointCloud-C 数据集上分别取得了 18.4% 和 16.3% 的错误率，相对于同类方法分别提高了 5.2% 和 4.2%。

CSI：提升三维点云识别对冲突的鲁棒性

CSI: Enhancing the Robustness of 3D Point Cloud Recognition against  Corruption

We introduce WyPR, a Weakly-supervised framework for Point cloud Recognition,
requiring only scene-level class tags as supervision. WyPR jointly addresses
three core 3D recognition tasks: point-level semantic segmentation, 3D proposal
generation, and 3D object detection, coupling their predictions through self
and cross-task consistency losses. We show that in conjunction with standard
multiple-instance learning objectives, WyPR can detect and segment objects in
point cloud data without access to any spatial labels at training time. We
demonstrate its efficacy using the ScanNet and S3DIS datasets, outperforming
prior state of the art on weakly-supervised segmentation by more than 6% mIoU.
In addition, we set up the first benchmark for weakly-supervised 3D object
detection on both datasets, where WyPR outperforms standard approaches and
establishes strong baselines for future work.

WyPR 是一种仅需要场景级别标签作为监督的弱监督点云识别框架，可联合解决点级语义分割、3D 建议生成和 3D 目标检测等三个核心任务，通过自身和跨任务一致性损失耦合它们的预测。在多实例学习目标的辅助下，WyPR 能在训练时不需要访问任何空间标签的情况下对点云数据中的物体进行检测和分割，并使用 ScanNet 和 S3DIS 数据集证明了其有效性，在弱监督分割方面优于先前的最新技术 6％以上。此外，我们还在两个数据集上开展了弱监督 3D 目标检测的第一次基准测试，结果 WyPR 优于标准方法，并为未来的工作建立了强基础。

没有空间标记的 3D 空间识别

3D Spatial Recognition without Spatially Labeled 3D

Despite the recent active research on processing point clouds with deep
networks, few attention has been on the sensitivity of the networks to
rotations. In this paper, we propose a deep learning architecture that achieves
discrete $\mathbf{SO}(2)$/$\mathbf{SO}(3)$ rotation equivariance for point
cloud recognition. Specifically, the rotation of an input point cloud with
elements of a rotation group is similar to shuffling the feature vectors
generated by our approach. The equivariance is easily reduced to invariance by
eliminating the permutation with operations such as maximum or average. Our
method can be directly applied to any existing point cloud based networks,
resulting in significant improvements in their performance for rotated inputs.
We show state-of-the-art results in the classification tasks with various
datasets under both $\mathbf{SO}(2)$ and $\mathbf{SO}(3)$ rotations. In
addition, we further analyze the necessary conditions of applying our approach
to PointNet based networks. Source codes at
this https URL

该论文提出了一种深度学习架构，能够在点云识别中实现离散的 SO（2）/SO（3）旋转等变性，通过消除置换并进行操作，提升了任何现有点云网络的性能，并在各种旋转下，展示了分类任务的最新成果。