Voxel Cloud Connectivity Segmentation - Supervoxels for Point Clouds

By Jeremie Papon, Alexey Abramov, Markus Schoeler, Florentin Wörgötter. 2013

578 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

3D fully convolutional network for vehicle detection in point cloud (2016, background): “ority of 3D detection algorithms can be summarized as two stages, i.e. candidate proposal and classiﬁcation. Candidates can be proposed by delicate segmentation algorithms [2], [5], [11], [14], [21], [22], [28], [29], [31], sliding window [30], random sampling [13], or the recently popular Region Pr”
Vehicle Detection from 3D Lidar Using Fully Convolutional Network (2016, background): “More delicate segmentation can be obtained by forming graphs on the point cloud [32, 14, 21, 29, 30].”
3D Semantic Parsing of Large-Scale Indoor Spaces (2016, methodology): “For instance, [30, 24] proposed an RGB-D segmentation method using a set of heuristics for leveraging 3D geometric priors.”
Deep Learning Advances in Computer Vision with 3D Data (2017, methodology): “Inspired from the techniques used in the 2D/image domain, several methods ranging from region growing (e.g., Vo et al. [2015]) and graph-based approaches (e.g., Sima and Nuchter [2013]) to superpixels (e.g., Papon et al. [2013] and Aijazi et al. [2013]) have been considered for segmenting 3D data.”
Incremental and Enhanced Scanline-Based Segmentation Method for Surface Reconstruction of Sparse LiDAR Data (2016, methodology): “[10] propose a method that segments the point cloud according to the connectivity of the voxels into a supervoxel, which is similar to a superpixel for image segmentation.”
DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics (2020, unknown): “The exploration is sequential and follows 5 main steps: • The visual scene is over-segmented using Voxel Cloud Connectivity Segmentation [68].”
Sensor fusion for semantic segmentation of urban scenes (2015, methodology): “We describe each of the steps in more detail below.”
Multi-scale object candidates for generic object tracking in street scenes (2016, methodology): “the VCCS algorithm [26] to partition the point cloud into segments.”
PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation (2018, methodology): “In [19] handcrafted voxel feature is used to model geometric relationship, and in [20] 2D CNN features from RGBD images are extracted.”