Publication | Closed Access
KinectFusion: Real-time dense surface mapping and tracking
300
Citations
0
References
2011
Year
Unknown Venue
Geometric ModelingAccurate Real-time MappingMachine VisionImage AnalysisEngineering3D VisionNatural SciencesComputer Stereo VisionField RoboticsExtended RealityArbitrary Indoor ScenesComputational ImagingDepth MapMulti-view GeometryStructure From MotionVariable Lighting ConditionsComputational GeometryComputer Vision
The paper presents a system that enables accurate real‑time mapping of complex indoor scenes under variable lighting using only a low‑cost depth camera and commodity graphics hardware. The system fuses depth data from a Kinect sensor into a single global implicit surface model and simultaneously tracks the sensor pose with a coarse‑to‑fine ICP algorithm that leverages all observed depth data. Experiments show that tracking against the growing full surface model yields constant‑time, low‑drift, high‑accuracy results in room‑sized scenes, outperforming frame‑to‑frame tracking, and demonstrate that real‑time dense surface reconstruction with commodity hardware is feasible and superior to passive computer vision approaches.
We present a system for accurate real-time mapping of complex and arbitrary indoor scenes in variable lighting conditions, using only a moving low-cost depth camera and commodity graphics hardware. We fuse all of the depth data streamed from a Kinect sensor into a single global implicit surface model of the observed scene in real-time. The current sensor pose is simultaneously obtained by tracking the live depth frame relative to the global model using a coarse-to-fine iterative closest point (ICP) algorithm, which uses all of the observed depth data available. We demonstrate the advantages of tracking against the growing full surface model compared with frame-to-frame tracking, obtaining tracking and mapping results in constant time within room sized scenes with limited drift and high accuracy. We also show both qualitative and quantitative results relating to various aspects of our tracking and mapping system. Modelling of natural scenes, in real-time with only commodity sensor and GPU hardware, promises an exciting step forward in augmented reality (AR), in particular, it allows dense surfaces to be reconstructed in real-time, with a level of detail and robustness beyond any solution yet presented using passive computer vision.