Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds)

2018-03-20 · Fabian Groh, Patrick Wieschollek, Hendrik P. A. Lensch

Traditional convolution layers are specifically designed to exploit the natural data representation of images -- a fixed and regular grid. However, unstructured data like 3D point clouds containing irregular neighborhoods constantly breaks the grid-based data assumption. Therefore applying best-practices and design choices from 2D-image learning methods towards processing point clouds are not readily possible. In this work, we introduce a natural generalization flex-convolution of the conventional convolution layer along with an efficient GPU implementation. We demonstrate competitive performance on rather small benchmark sets using fewer parameters and lower memory consumption and obtain significant improvements on a million-scale real-world dataset. Ours is the first which allows to efficiently process 7 million points concurrently.

📄 PDF Abstract BibTeX arXiv:1803.07289

Code (1)

cgtuebingen/Flex-Convolution tf

Tasks

Classify 3D Point CloudsGPUSemantic Segmentation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Deep FusionNet for Point Cloud Semantic Segmentation

2020-08-01 · ECCV 2020 8 · Feihu Zhang Jin Fang Benjamin Wah Philip Torr

Many point cloud segmentation methods rely on transferring irregular points into a voxel-based regular representation. Although voxel-based convolutions are useful for feature aggregation, they produce ambiguous or wrong…

3D Semantic Segmentation GPU Point Cloud Segmentation Segmentation+1

Tangent Convolutions for Dense Prediction in 3D

2018-07-06 · CVPR 2018 6 · Maxim Tatarchenko, Jaesik Park, Vladlen Koltun, Qian-Yi Zhou

We present an approach to semantic scene analysis using deep convolutional networks. Our approach is based on tangent convolutions - a new construction for convolutional networks on 3D data. In contrast to volumetric app…

3D Semantic Segmentation Prediction Semantic Segmentation

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

2017-11-27 · CVPR 2018 6 · Loic Landrieu, Martin Simonovsky

We propose a novel deep learning-based framework to tackle the challenge of semantic segmentation of large-scale point clouds of millions of points. We argue that the organization of 3D point clouds can be efficiently ca…

3D Semantic Segmentation Semantic Segmentation

ConvPoint: Continuous Convolutions for Point Cloud Processing

2019-04-04 · Alexandre Boulch

Point clouds are unstructured and unordered data, as opposed to images. Thus, most machine learning approach developed for image cannot be directly transferred to point clouds. In this paper, we propose a generalization …

3D Part Segmentation 3D Semantic Segmentation General Classification LIDAR Semantic Segmentation+2

DublinCity: Annotated LiDAR Point Cloud and its Applications

2019-09-06 · S. M. Iman Zolanvari, Susana Ruano, Aakanksha Rana, Alan Cummins 외

Scene understanding of full-scale 3D models of an urban area remains a challenging task. While advanced computer vision techniques offer cost-effective approaches to analyse 3D urban elements, a precise and densely label…

3D Reconstruction Scene Understanding