paper-with-me

홈 › Papers

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

2021-05-04 · ICCV 2021 10 · Tiange Xiang, Chaoyi Zhang, Yang song, Jianhui Yu, Weidong Cai

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.

📄 PDF Abstract BibTeX arXiv:2105.01288

Code (3)

tiangexiang/CurveNet 공식 구현 pytorch
RF5/CurveNet pytorch
vinits5/learning3d pytorch

Tasks

3D Part Segmentation3D Point Cloud ClassificationGeneral ClassificationPoint Cloud Classification

Similar Papers 제목 키워드 기반

CloudWalker: Random walks for 3D point cloud shape analysis

2021-12-02 · Adi Mesika, Yizhak Ben-Shabat, Ayellet Tal

Point clouds are gaining prominence as a method for representing 3D shapes, but their irregular structure poses a challenge for deep learning methods. In this paper we propose CloudWalker, a novel method for learning 3D …

Retrieval

Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction

2025-05-04 · Cheng Wang, Xinzhu Ma, Bin Wang, Shixiang Tang 외

Recovering CAD models from point clouds, especially the sketch-extrusion process, can be seen as the process of rebuilding the topology and extrusion primitives. Previous methods utilize implicit fields for sketch repres…

CAD Reconstruction

Reassembling Broken Objects using Breaking Curves

2023-06-05 · Ali Alagrami, Luca Palmieri, Sinem Aslan, Marcello Pelillo 외

Reassembling 3D broken objects is a challenging task. A robust solution that generalizes well must deal with diverse patterns associated with different types of broken objects. We propose a method that tackles the pairwi…

Object

Reconstructing Thin Structures of Manifold Surfaces by Integrating Spatial Curves

2018-06-01 · CVPR 2018 6 · Shiwei Li, Yao Yao, Tian Fang, Long Quan

The manifold surface reconstruction in multi-view stereo often fails in retaining thin structures due to incomplete and noisy reconstructed point clouds. In this paper, we address this problem by leveraging spatial curve…

Surface Reconstruction

MeshWalker: Deep Mesh Understanding by Random Walks

2020-06-09 · Alon Lahav, Ayellet Tal

Most attempts to represent 3D shapes for deep learning have focused on volumetric grids, multi-view images and point clouds. In this paper we look at the most popular representation of 3D shapes in computer graphics - a …

3D Classification3D Object RecognitionSemantic Segmentation