Elastic Fragments for Dense Scene Reconstruction

By Qian-Yi Zhou, Stephen D. Miller, Vladlen Koltun. 2013

119 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

OctNetFusion: Learning Depth Fusion from Data (2017, background): “The problem of calibration and loop-closure detection has been considered in [6, 57].”
Robust reconstruction of indoor scenes (2015, background): “These scene fragments integrate out some of the noise in the range data and yield more reliable normal information [69, 72].”
ElasticFusion: Real-time dense SLAM and light source estimation (2016, methodology): “The approach we have developed in this paper is closer to the offline dense scene reconstruction system of Zhou et al. (2013) than a traditional SLAM system in how it places much more emphasis on the accuracy of the reconstructed map over the estimated trajectory.”
BigBIRD: A large-scale 3D database of object instances (2014, background): “Recent work demonstrates that KinectFusion variants can provide high-quality 3D reconstructions [21], [22], [23], [24].”
Online Reconstruction of Indoor Scenes from RGB-D Streams (2016, methodology): “An exception is [38], in which the authors mentioned that the calibration approach of [28] has been applied to their sensor.”
PointNetLK: Robust & Efficient Point Cloud Registration Using PointNet (2019, methodology): “e-art in object classiﬁcation and segmentation on point clouds. * equal contribution. Figure 1: Point cloud registration of a (Top) Stanford bunny [38] and (Bottom) partial scan of reading room scene [46] with PointNetLK. Refer to Sec.4.2and Sec.4.4 for more details. As the iterations progress, Poin”
Fusion++: Volumetric Object-Level SLAM (2018, background): “Unlike many dense reconstruction systems [24, 39, 43, 38, 3, 8] we make no attempt to keep a dense representation of the entire scene.”
Range sensor and silhouette fusion for high-quality 3D Scanning (2015, methodology): “We employ a CPU implementation of KinectFusion that represents the TSDF structure using an octree; specifically, we adopt the implementation used in [33].”
ElasticFusion: Dense SLAM Without A Pose Graph (2015, background): “than a traditional SLAM system in how it places much more emphasis on the accuracy of the reconstructed map over the estimated trajectory [27].”
SceneNN: A Scene Meshes Dataset with aNNotations (2016, background): “Zhou and Koltun [46] proposed to deform the fragments using control lattices for nonrigid alignment.”