Real-Time Large-Scale Dense 3D Reconstruction with Loop Closure

By Olaf Kähler, Victor Adrian Prisacariu, David William Murray. 2016

134 citations recorded by the source corpus.

In the highly active research field of dense 3D reconstruction and modelling, loop closure is still a largely unsolved problem. While a number of previous works show how to accumulate keyframes, globally optimize their pose on closure, and compute a dense 3D model as a post-processing step, in this paper we propose an online framework which delivers a consistent 3D model to the user in real time. This is achieved by splitting the scene into submaps, and adjusting the poses of the submaps as and when required. We present a novel technique for accumulating relative pose constraints between the submaps at very little computational cost, and demonstrate how to maintain a lightweight, scalable global optimization of submap poses. In contrast to previous works, the number of submaps grows with the observed 3D scene surface, rather than with time. In addition to loop closure, the paper incorporates relocalization and provides a novel way of assessing tracking quality.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

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

In Geology

Citations in the corpus

ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes (2017, background): “There is a large variety of algorithms targeting this scenario [59, 88, 7, 62, 37, 89, 42, 9, 90, 38, 12].”
Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representation (2022, methodology): “Following this basic design, many systems gain improvements by introducing different 3D structures [38], exploring space subdivision [21, 24] and performing global map optimization [11,13,26].”
NICE-SLAM: Neural Implicit Scalable Encoding for SLAM (2021, unknown): “, KinectFusion [28] among other works [5, 14, 18, 33].”
Deep Global Registration (2020, result): “ElasticFusion [42] InfiniTAM [20] BAD-SLAM [38] Multi-way + FGR [49] Multi-way + RANSAC [50] Multi-way + Ours”
BAD SLAM: Bundle Adjusted Direct RGB-D SLAM (2019, background): “Fragment-based optimization fuses together chunks of frames into fragments and then optimizes the global (rigid) fragment alignment [6,15,27,49].”
A Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation (2016, unknown): “In [41], loop closure was enabled by splitting the scene into submaps.”