This paper presents ViewFormer, a simple yet effective model for multi-view
3d shape recognition and retrieval. We systematically investigate the existing
methods for aggregating multi-view information and propose a novel ``view set"
perspective, which minimizes the relation assumption about the views and
releases the representation flexibility. We devise an adaptive attention model
to capture pairwise and higher-order correlations of the elements in the view
set. The learned multi-view correlations are aggregated into an expressive view
set descriptor for recognition and retrieval. Experiments show the proposed
method unleashes surprising capabilities across different tasks and datasets.
For instance, with only 2 attention blocks and 4.8M learnable parameters,
ViewFormer reaches 98.8% recognition accuracy on ModelNet40 for the first time,
exceeding previous best method by 1.1% . On the challenging RGBD dataset, our
method achieves 98.4% recognition accuracy, which is a 4.1% absolute
improvement over the strongest baseline. ViewFormer also sets new records in
several evaluation dimensions of 3D shape retrieval defined on the SHREC'17
benchmark.

本研究为多视角三维形状识别和检索提出了 ViewFormer 方法，该方法通过提出 “视角集” 视角，采用一种自适应的注意力模型来捕捉视图集中的元素之间的成对和高阶相关性，并将学习到的多视角相关性聚合到一个富有表达力的视角集描述符中进行识别和检索。实验证明，该方法在不同任务和数据集上具有惊人的能力。特别是在 ModelNet40 数据集上，ViewFormer 首次达到 98.8％的识别准确率，超过了之前最好的方法 1.1％的表现。

ViewFormer: 多视角三维形状理解的视图集合注意力

ViewFormer: View Set Attention for Multi-view 3D Shape Understanding

While there has been a number of studies on Zero-Shot Learning (ZSL) for 2D
images, its application to 3D data is still recent and scarce, with just a few
methods limited to classification. We present the first generative approach for
both ZSL and Generalized ZSL (GZSL) on 3D data, that can handle both
classification and, for the first time, semantic segmentation. We show that it
reaches or outperforms the state of the art on ModelNet40 classification for
both inductive ZSL and inductive GZSL. For semantic segmentation, we created
three benchmarks for evaluating this new ZSL task, using S3DIS, ScanNet and
SemanticKITTI. Our experiments show that our method outperforms strong
baselines, which we additionally propose for this task.

本研究提出了一种新的基于生成模型的零样本学习方法，能够处理包括分类和语义分割在内的三维数据，在 ModelNet40 数据集上表现良好，并在 S3DIS，ScanNet 和 SemanticKITTI 数据集上进行了验证。

生成式零样本学习用于三维点云语义分割

Generative Zero-Shot Learning for Semantic Segmentation of 3D Point  Clouds

Discrete point cloud objects lack sufficient shape descriptors of 3D
geometries. In this paper, we present a novel method for aggregating
hypothetical curves in point clouds. Sequences of connected points (curves) are
initially grouped by taking guided walks in the point clouds, and then
subsequently aggregated back to augment their point-wise features. We provide
an effective implementation of the proposed aggregation strategy including a
novel curve grouping operator followed by a curve aggregation operator. Our
method was benchmarked on several point cloud analysis tasks where we achieved
the state-of-the-art classification accuracy of 94.2% on the ModelNet40
classification task, instance IoU of 86.8 on the ShapeNetPart segmentation
task, and cosine error of 0.11 on the ModelNet40 normal estimation task.

本文提出了一种新颖的点云曲线聚合方法，该方法首先在点云中进行诱导游走，然后再将曲线聚合起来，以增强其点级特征。该方法在多个点云分析任务上进行了基准测试，在 ModelNet40 分类任务中达到 94.2％的分类准确度，在 ShapeNetPart 分割任务中获得 86.8 的实例 IoU，在 ModelNet40 正常估计任务中获得 0.11 的余弦误差，表现出卓越的性能。