Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis

By Tiange Xiang, Chaoyi Zhang, Yang Song, Jianhui Yu, Weidong (Tom) Cai. IEEE International Conference on Computer Vision, 2021

383 citations recorded by the source corpus.

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 pointwise 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. Our project page with source code is available at: https://curvenet.github.io/.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Geology

View Paper: https://www.semanticscholar.org/paper/137303eaded96d4fc531f4f807c5684b04894170

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Guocheng Qian
2. Yu Qiao
3. Bin Cui
4. Peng Gao
5. Hasan Hammoud
6. Jinjie Mai
7. Mohamed Elhoseiny
8. Kunchang Li

In Computer Graphics and Computer-Aided Design

1. Yu Qiao
2. Mohamed Elhoseiny
3. Bernard Ghanem
4. Hongsheng Li

In Geology

1. Guocheng Qian
2. Yu Qiao
3. Peng Gao
4. Hasan Hammoud
5. Jinjie Mai
6. Mohamed Elhoseiny
7. Renrui Zhang
8. Houwen Peng

Citations in the corpus

• PointCLIP: Point Cloud Understanding by CLIP (2021, methodology): “Also for CurveNet [60], the state-of-the-art 3D recognition network, the knowledge ensemble contributes to performance boost from 93.”
• PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies (2022, positive): “0 %). to that of the SOTA CurveNet [48] and outperforms a large number of representative networks, such as KPConv [41] and ASSANet [30] in terms of both instance mean IoU (ins. mIoU) and throughput.”