Dense scene reconstruction with points of interest

By Qian-Yi Zhou, Vladlen Koltun. 2013

279 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

Elastic Fragments for Dense Scene Reconstruction (2013, methodology): “Current techniques for dense scene reconstruction from consumer-grade range video cast the problem in terms of trajectory estimation [16, 7, 34, 35].”
RGBD Datasets: Past, Present and Future (2016, methodology): “Robust Reconstruction Datasets [118] Asus Xtion Pro 8 X ’13”
Real-Time Large-Scale Dense 3D Reconstruction with Loop Closure (2016, background): “The data for the top sequence is from [38].”
A Field Model for Repairing 3D Shapes (2016, background): “Recent advances of 3D acquisition devices and 3D scene reconstruction research [28, 38, 39, 40, 4] have enabled large-scale acquisition of 3D scene data and this has raised”
Online Reconstruction of Indoor Scenes from RGB-D Streams (2016, methodology): “Through projection we can compute its distance to the ith camera, denoted by Ci(p), and the depth value on the projected pixel Di(π(p)).”
SceneNN: A Scene Meshes Dataset with aNNotations (2016, unknown): “[44].”
Real-time 3D reconstruction at scale using voxel hashing (2013, background): “While these types of efficient spatial hashing techniques have been proposed for a variety of rendering and collision detection tasks [Teschner et al. 2003; Lefebvre and Hoppe 2006; Bastos and Celes 2008; Alcantara et al. 2009; Pan and Manocha 2011; Garcı́a et al. 2011], we describe the use of such…”
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction (2020, methodology): “combe3 1 University of North Carolina at Chapel Hill 2 TU Dortmund University 3 Facebook Reality Labs Fig.1: Reconstruction performed by our Deep Local Shapes (DeepLS) of the Burghers of Calais scene [56]. DeepLS represents surface geometry as a sparse set of local latent codes in a voxel grid, as s”
ElasticFusion: Dense SLAM Without A Pose Graph (2015, methodology): “This dataset was made available courtesy of Zhou and Koltun [26].”
Robust reconstruction of indoor scenes (2015, background): “Prior work on scene reconstruction with consumer depth cameras recognized the importance of global registration [29, 18, 69, 62, 65].”
A Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation (2016, methodology): “The dataset includes six scenes from publicly available datasets: the copyroom and lounge from the Stanford dataset [38], the hotel and dorm from the SUN3D [3], and the kitchen and office sequences from the Microsoft dataset [56].”
ElasticFusion: Real-time dense SLAM and light source estimation (2016, methodology): “This dataset was made available courtesy of Zhou and Koltun (2013).”
Tanks and temples (2017, methodology): “While to date use structure priors [Furukawa et al. 2009; Ikehata et al. 2015; Xiao and Furukawa 2014] or depth cameras [Choi et al. 2015; Zhou and Koltun 2013].”
Real-time large-scale dense RGB-D SLAM with volumetric fusion (2014, methodology): “Similar work also by Zhou and Koltun (2013) presents a method which detects points of interest in a scene and specifically optimises the camera trajectory to preserve detailed geometry around these points, within an offline frame.”
School of Electrical and Computer Engineering Oklahoma State University , Stillwater , OK 74078 , USA (methodology): “In contrast, the main intention of the researchers in the computer vision community is dense modeling and enhancing the quality and fidelity of the reconstructed models [22, 29, 19, 4].”