Live dense reconstruction with a single moving camera

By Richard A. Newcombe, Andrew J. Davison. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

460 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/51a5cdbc2322c0f3ae22b732e471cc48ec7791e5

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

Visual SLAM algorithms: a survey from 2010 to 2016 (2017, background): “Since PTAM can reconstruct a sparse 3D structure of the environment only, the third thread can be used to reconstruct a dense 3D structure of the environment [32, 33].”
Shading-based refinement on volumetric signed distance functions (2015, methodology): “Recent methods for 3D scene reconstruction from a hand-held RGB camera use a combination of sparse feature tracking, structure-from-motion, and stereo to reconstruct the scene geometry by integration in an SDF [Newcombe and Davison 2010; Pradeep et al. 2013].”
RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments (2012, background): “Newcombe and Davison (2010) developed an impressive system that does real-time dense 3D reconstruction with a monocular camera, although their system is still limited to small feature-rich scenes.”
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction (2020, methodology): “This representation has been used by many classical methods to represent and optimize geometry based on raw sensor observations [12,31,48,37,38].”
KinectFusion: Real-time dense surface mapping and tracking (2011, methodology): “By using only depth data, our system can work in complete darkness mitigating any issues concerning low light conditions, problematic for passive camera [17, 19, 26] and RGB-D based systems [14].”
Elastic Fragments for Dense Scene Reconstruction (2013, background): “Substantial progress on dense scene reconstruction from photographs and video sequences has been made, despite the ambiguity of photometric cues [20, 26, 21, 6, 15, 17].”
Robust reconstruction of indoor scenes (2015, methodology): “The influential KinectFusion system demonstrated realtime dense reconstruction with a consumer depth camera [46], building on earlier work on range image integration [14], visual odometry [15, 48, 38], and real-time 3D reconstruction [51, 49, 45].”
Online Reconstruction of Indoor Scenes from RGB-D Streams (2016, background): “Attempts at real-time dense surface modelling from passive cameras to date have had limited results, most- ∗indicates equal contributions and joint first authors ly on outdoor scenes [23, 30], small objects and compact workspaces [16, 18, 24].”
Real-Time Large-Scale Dense 3D Reconstruction with Loop Closure (2016, background): “The prompt delivery of highly detailed dense reconstructions of the 3D environment is currently one of the major frontiers in computer vision [1–6].”
KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera (2011, methodology): “No explicit feature detection Unlike structure from motion (SfM) systems (e.g. [15]) or RGB plus depth (RGBD) techniques (e.g. [12, 13]), which need to robustly and continuously detect sparse scene features, our approach to camera tracking avoids an explicit detection step, and directly works on the”
PL-SLAM: Real-time monocular visual SLAM with points and lines (2017, methodology): “To solve this, dense and direct methods can be applied, even though they are likely to be computationally expensive [19], [21], and require dedicated GPU-implementations to achieve real-time performance.”
DTAM: Dense tracking and mapping in real-time (2011, methodology): “For use in tracking, we compute a triangle mesh from the inverse depth map, culling oblique edges as described in [9].”
Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representation (2022, methodology): “Traditional SLAM methods using either feature matching [3, 16–18], nonlinear energy minimization [20], or a combination of both [7,39] to solve the camera poses.”