3DMatch: Learning the Matching of Local 3D Geometry in Range Scans

By Andy Zeng, Shuran Song, Matthias Nießner, Matthew Fisher, Jianxiong Xiao. 2016

91 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis (2016, background): “Since then different versions of 3D-CNN architectures have been proposed in order to improve classiﬁcation accuracy [22, 31, 34], obtain object proposals [37], or match local 3D geometry [46].”
Semantic Scene Completion from a Single Depth Image (2016, background): “(a) Object centric networks [34, 20] (b) 3DMatch [36] (c) Deep Sliding Shape [31] (d) SSCNet”
Single Image 3D Interpreter Network (2016, background): “Depth-/mesh-based models can recover detailed 3D object structure from a single image, either by adapting existing 3D models from a database [3,19,6,8,20,21,22,23,24], or by inferring from its detected 2D silhouette [5,7,4].”
Multi-view self-supervised deep learning for 6D pose estimation in the Amazon Picking Challenge (2016, methodology): “The second uses more elaborated local descriptors such as SIFT keypoints [10] for color data or 3DMatch [11] for 3D data.”
Fully Convolutional Geometric Features (2019, methodology): “We used the 3DMatch registration set [36] to evaluate the registration recall of FCGF.”
TEASER: Fast and Certifiable Point Cloud Registration (2020, methodology): “We evaluate TEASER++’s performance in such scenarios using the 3DMatch dataset [38], which consists of RGB-D scans from 62 real-world indoor scenes.”
Self-Supervised Visual Descriptor Learning for Dense Correspondence (2017, methodology): “[32] also makes use of a generative model based on dense fusion to provide automated labelling, computing descriptors on 3D fused geometry fragments at sparse 3D keypoints.”
Geometric deep learning (2016, background): “A wide range of applications have been recently introduced that process 3D geometric shapes, such as highly effective 3D object detection for RGB-D data [82], object classifcation of point clouds [61], 3D local feature matching [106], and 3D deformation ﬂows [103].”
PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition (2018, background): “Additionally, 3DMatch [51] that learns local descriptors for smallscale indoor scenes and Vote3D [48] for object detection on the outdoor KITTI dataset.”
LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis (2018, background): “ation, such as the volumetric CNNs proposed in [15] and 3D ShapeNets designed in [26] are suitable for point cloud-based classiﬁcation and recognition, respectively. Moreover, Vote3D [23] and 3DMatch [29] were designed for local feature learning of small-scacle outdoor and indoor environments, respe”
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks (2019, background): “2D perception as well as 3D reconstruction [4], feature learning [34], and semantic segmentation [5].”