KinectFusion: Real-time dense surface mapping and tracking
The DOI matches its Crossref record; 32 of the 34 references it cites were found in a registry or an index.
Abstract
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.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
A method for registration of 3-D shapes
Besl, P. J., & McKay, N. D. (1992) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.121791 · Cited by 18,103 · cited 2×
“The most important class of algorithms have been based on the ICP concept introduced in [3] which poses data alignment as a nonlinear optimisation problem in which correspondences between scans are approximated using the closest pairs of points found between scans at the previous iteration.”
BackgroundMethodMarching cubes: A high resolution 3D surface construction algorithm
Lorensen, W. E., & Cline, H. E. (1987) · Proceedings of the 14th annual conference on Computer graphics and interactive techniques · doi:10.1145/37401.37422 · Cited by 10,104 · cited 1×
“One option is to extract the connected surfaces using a marching cubes type algorithm [18], followed by a standard rasterising rendering pipeline.”
MethodBilateral Filtering for Gray and Color Images
Tomasi, C., & Manduchi, R. (2002) · Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271) · doi:10.1109/iccv.1998.710815 · Cited by 8,177 · cited 1×
“We apply a bilateral filter [27] to the raw depth map to obtain a discontinuity preserved depth map with reduced noise Dk,”
MethodParallel Tracking and Mapping for Small AR Workspaces
Klein, G., & Murray, D. (2007) · 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2007.4538852 · Cited by 4,346 · cited 3×
“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].”
BackgroundMethodObject modelling by registration of multiple range images
Chen, Y., & Medioni, G. (1992) · Image and Vision Computing · doi:10.1016/0262-8856(92)90066-c · Cited by 3,154
A volumetric method for building complex models from range images
Curless, B., & Levoy, M. (1996) · Proceedings of the 23rd annual conference on Computer graphics and interactive techniques · doi:10.1145/237170.237269 · Cited by 3,124 · cited 6×
“A related non-parametric representation used in graphics is the signed distance function (SDF) introduced in [7] for the purpose of fusing partial depth scans while mitigating problems related to mesh-based reconstruction algorithms.”
BackgroundMethodInfluentialA Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms
Seitz, S. M., Curless, B., Diebel, J., Scharstein, D., & Szeliski, R. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1 (CVPR'06) · doi:10.1109/cvpr.2006.19 · Cited by 2,457 · cited 1×
“In computer vision, research on structure from motion (SFM) and multi-view stereo (MVS) has produced many compelling re-sults, in particular accurate camera tracking and sparse reconstructions (e.g. [10]), and increasingly reconstruction of dense surfaces (e.g. [24]).”
BackgroundIterative point matching for registration of free-form curves and surfaces
Zhang, Z. (1994) · International Journal of Computer Vision · doi:10.1007/bf01427149 · Cited by 2,402 · cited 1×
“A number of ICP variants perform early iterations on a subset of possibly corresponding points or operate within a coarse-to-fine scheme [31], speeding up both the data association and final pose optimisation.”
BackgroundKinectFusion: real-time 3D reconstruction and interaction using a moving depth camera
Izadi, S., Kim, D., Hilliges, O., Molyneaux, D., Newcombe, R., Kohli, P., Shotton, J., Hodges, S., Freeman, D., Davison, A., et al. (2011) · Proceedings of the 24th annual ACM symposium on User interface software and technology · doi:10.1145/2047196.2047270 · Cited by 2,110 · cited 1×
“In [16] we discuss all these possibilities in detail.”
BackgroundSelf-citationDTAM: Dense tracking and mapping in real-time
Newcombe, R. A., Lovegrove, S. J., & Davison, A. J. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126513 · Cited by 2,078
Self-citation
Research works printed but not linked: 4
- weise, 0, Inhand scanning with online loop closure, Proceedings of the IEEE International Workshop on 3D Digital Imaging and Modeling (3DIM) 2009
- wurm, 0, OctoMap: A probabilistic, flexible, and compact 3D map representation for robotic systems, Proceedings of the ICRA Workshop on Best Practice in 3D Perception and Modeling for Mobile Manipulation 2010
- 0, NVIDIA OptiX 2 Ray Tracing Engine
- zach, 0, A globally optimal algorithm for robust TV-L1 range image integration, Proceedings of the International Conference on Computer Vision (ICCV) 2007
Cited by
Items 601–700 of 1,006
Vision guided robotic inspection for parts in manufacturing and remanufacturing industry
Khan, A., Mineo, C., Dobie, G., MacLeod, C., & Pierce, G. (2020) · Journal of remanufacturing · doi:10.1007/s13243-020-00091-x · Cited by 75
“Kinectfusion [18, 31] is recommended for achieving the 3D reconstruction of static objects or indoor scenes for mobile applications with a tracking absolute error of 2.1-7.0 cm.”
BackgroundInfluentialElasticity Meets Continuous-Time: Map-Centric Dense 3D LiDAR SLAM
Park, C., Moghadam, P., Williams, J., Kim, S., Sridharan, S., & Fookes, C. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3096650 · Cited by 76
ROBI: A Multi-View Dataset for Reflective Objects in Robotic Bin-Picking
Yang, J., Gao, Y., Li, D., & Waslander, S. L. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9635871 · Cited by 75
“To evaluate depth fusion methods, for each scene, we constructed a ground truth mesh by applying TSDF fusion [29] on ground truth depth maps.”
MethodA comprehensive overview of core modules in visual SLAM framework
Cai, D., Li, R., Hu, Z., Lu, J., Li, S., & Zhao, Y. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127760 · Cited by 75
PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations
Zheng, Y., Zhao, Q., Yang, G., Wang, Y., Xiang, D., Dubost, F., Lagun, D., Beeler, T., Tombari, F., Guibas, L. J., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72913-3_15 · Cited by 75
Aggressive Deep Driving: Combining Convolutional Neural Networks and Model Predictive Control
Drews, P., Williams, G., Goldfain, B., Theodorou, E. A., & Rehg, J. M. (2017) · Conference on Robot Learning · Cited by 75
DRE-SLAM: Dynamic RGB-D Encoder SLAM for a Differential-Drive Robot
Yang, D., Bi, S., Wang, W., Chang, Y., Wang, W., Qi, X., & Cai, Y. (2019) · Remote Sensing · doi:10.3390/rs11040380 · Cited by 75
“Point cloud [12], surfel [2], and volumetric [13,14] representations are three commonly used dense environment representations [4].”
BackgroundOnline LiDAR-SLAM for Legged Robots with Robust Registration and Deep-Learned Loop Closure
Ramezani, M., Tinchev, G., Egor, I., & Fallon, M. F. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196769 · Cited by 75
“Works such as [9] and [10] leveraged the frame-to-model visual tracking of KinectFusion [11] or ElasticFusion [12], which use a coarse-to-fine ICP algorithm.”
MethodLarge-scale outdoor 3D reconstruction on a mobile device
Schöps, T., Sattler, T., Häne, C., & Pollefeys, M. (2016) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.09.007 · Cited by 74
“Following the popular KinectFusion approach [1], methods [3–6] based on RGBD data usually utilize a volumetric approach modeling the truncated signed distance function (TSDF) of the surface in the scene [7].”
BackgroundMethodInfluentialLing, H. (2017) · IEEE Multimedia · doi:10.1109/mmul.2017.3051517 · Cited by 74
Laidlow, T., Czarnowski, J., & Leutenegger, S. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793527 · Cited by 74
“One option to resolve these issues in monocular dense reconstruction is through the use of a depth camera (the approach taken by [12] and [13]), but depth cameras have limited range, consume more power, and do not typically work outdoors or in strong sunlight.”
BackgroundNEDS-SLAM: A Neural Explicit Dense Semantic SLAM Framework Using 3D Gaussian Splatting
Ji, Y., Liu, Y., Xie, G., Ma, B., Xie, Z., & Liu, H. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3451390 · Cited by 74
“V ISUAL SLAM (Simultaneous Localization and Mapping) is a fundamental research problem in robotics, which involves simultaneously tracking the camera pose and incrementally constructing a map of an unknown environment [1].”
BackgroundAccurate Estimation of Human Body Orientation From RGB-D Sensors
Liu, W., Zhang, Y., Tang, S., Tang, J., Hong, R., & Li, J. (2013) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2013.2272636 · Cited by 74
“opens up new opportunities to solve fundamental problems in computer vision, including robotic manipulation [16], human– computer interaction [9], [34], [38], [39], 3-D mapping and localization [13], [24], and so on.”
Lock3DFace: A large-scale database of low-cost Kinect 3D faces
Zhang, J., Huang, D., Wang, Y., & Sun, J. (2016) · International Conference on Biometrics · doi:10.1109/icb.2016.7550062 · Cited by 74
“In [27], the KinectFusion system is introduced, fusing all the depth data streamed from a Kinect sensor into a single global implicit high-quality surface model of the observed scene in real-time.”
MethodBonatti, R., Zhang, Y., Choudhury, S., Wang, W., & Scherer, S. (2020) · Springer proceedings in advanced robotics · doi:10.1007/978-3-030-33950-0_11 · Cited by 74
Playing Doom with SLAM-Augmented Deep Reinforcement Learning
Bhatti, S., Desmaison, A., Mikšík, O., Nardelli, N., Siddharth, N., & Torr, P. H. S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.00380 · Cited by 43
“KinectFusion-based approaches [33] sense depth measurements directly using active sensors and fuse them over time to recover high-quality surfaces, but they too suffer from the same issue.”
BackgroundPoint3R: Streaming 3D Reconstruction with Explicit Spatial Pointer MemoryPreprint
Wu, Y., Zheng, W., Zhou, J., & Lu, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.02863 · Cited by 74
“However, they often rely on specific camera motion assumptions [13, 40] (sometimes these motion assumptions may be misleading or restrictive) or require additional depth/LiDAR sensors [39] for better performance.”
Depth Estimation Method for Monocular Camera Defocus Images in Microscopic Scenes
Ban, Y., Liu, M., Wu, P., Yang, B., Liu, S., Yin, L., & Zheng, W. (2022) · Electronics · doi:10.3390/electronics11132012 · Cited by 73
Real-time pose estimation of deformable objects using a volumetric approach
Li, Y., Wang, Y., Case, M., Chang, S.-F., & Allen, P. K. (2014) · 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2014.6942687 · Cited by 65
“In addition to a smooth mesh, the KinectFusion library also generates a Signed Distance Function (SDF) mapping, which will be used for 3D feature extraction.”
MethodInfluentialVisual Odometry Algorithm Using an RGB-D Sensor and IMU in a Highly Dynamic Environment
Kim, D.-H., Han, S.-B., & Kim, J.-H. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-16841-8_2 · Cited by 73
“proposed a system, Kinectfusion for accurate real-time mapping of indoor scenes [22].”
BackgroundSelf-citation3D Reconstruction of “In-the-Wild” Faces in Images and Videos
Booth, J. G., Roussos, A., Ververas, E., Antonakos, E., Ploumpis, S., Panagakis, Y., & Zafeiriou, S. P. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2832138 · Cited by 73
“We employed the KinectFusion [63], [64] framework to acquire a 3D representation of the subjects with a Kinect v1 sensor.”
MethodA Survey of Simultaneous Localization and Mapping with an Envision in 6G Wireless Networks
Huang, B., Zhao, J., Luo, S., & Liu, J. (2021) · Journal of Global Positioning Systems · doi:10.5081/jgps.17.1.94 · Cited by 75
VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusion
Stier, N., Rich, A., Sen, P., & Höllerer, T. (2021) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv53792.2021.00042 · Cited by 72
“Although active depth sensors have been employed for this purpose [6, 29], they increase platform cost relative to passive cameras.”
BackgroundMethodRemoteFusion: real time depth camera fusion for remote collaboration on physical tasks
Adcock, M., Anderson, S., & Thomas, B. H. (2013) · ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry (VRCAI) · doi:10.1145/2534329.2534331 · Cited by 72
“The PCL imple-mentation is based on the KinectFusion [Newcombe et al. 2011; Izadi et al.”
MethodInfluentialCanelhas, D. R., Stoyanov, T., & Lilienthal, A. J. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696880 · Cited by 72
“As been suggested by [5], [6] either a uniform weight can be used, producing a “rolling average”, or the weight W can be related to an error model of the depth camera.”
BackgroundMUWA: Multi-field universal wheel for air-land vehicle with quad variable-pitch propellers
Kawasaki, K., Zhao, M., Okada, K., & Inaba, M. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696605 · Cited by 72
“These measurements were made with an Xtion (depth sensor) and PCL (Point Cloud Library).”
MethodDepth-based tracking with physical constraints for robot manipulation
Schmidt, T., Hertkorn, K., Newcombe, R. A., Márton, Z.-C., Suppa, M., & Fox, D. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7138989 · Cited by 72
“This could be done using a KinectFusion-style truncated signed distance function to represent the model, allowing the tracker to use the partial model for tracking with few changes to the method [19].”
MethodSelf-citationTemplateless Quasi-rigid Shape Modeling with Implicit Loop-Closure
Zeng, M., Zheng, J., Cheng, X., & Liu, X. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.26 · Cited by 72
“From this experiment, we show (1) Our result approximates the ground truth globally; (2) Both global rigid registration and KinectFusion are unable to compensate the obvious nonrigid deformation.”
MethodInfluentialWhen Can We Use KinectFusion for Ground Truth Acquisition
Meister, S., Izadi, S., Kohli, P., Hämmerle, M., Rother, C., & Kondermann, D. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · Cited by 72
Self-citationA survey on conventional and learning‐based methods for multi‐view stereo
Stathopoulou, E. K., & Remondino, F. (2023) · The Photogrammetric Record · doi:10.1111/phor.12456 · Cited by 71
Vision-based environmental perception for autonomous driving
Liu, F., Lu, Z., & Lin, X. (2023) · Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering · doi:10.1177/09544070231203059 · Cited by 71
Real-time monocular dense mapping on aerial robots using visual-inertial fusion
Yang, Z., Gao, F., & Shen, S. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989529 · Cited by 71
“An impressive result is given by KinectFusion [1], which takes the depth map measured by a Kinect as input, simultaneously localizes the camera itself using iterative closest point (ICP), and fuses all of the measurements into a global map using TSDF fusion.”
MethodTactile Mapping and Localization from High-Resolution Tactile Imprints
Bauzá, M., Canal, O., & Rodríguez, A. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794298 · Cited by 71
“With good visibility, visual information can be enough to recover and track most objects [7, 8, 9].”
Weakly-Supervised 3D Shape Completion in the Wild
Gu, J., Ma, W.-C., Manivasagam, S., Zeng, W., Wang, Z., Xiong, Y., Su, H., & Urtasun, R. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58558-7_17 · Cited by 71
GCN-Denoiser: Mesh Denoising with Graph Convolutional Networks
Shen, Y., Fu, H., Du, Z., Chen, X., Burnaev, E. V., Zorin, D., Zhou, K., & Zheng, Y. (2022) · ACM Transactions on Graphics · doi:10.1145/3480168 · Cited by 71
“• K-FData: This set contains meshes scanned by Microsoft Kinect v1 via the Kinect-Fusion technique [Newcombe et al. 2011].”
MethodNeural Refinement for Absolute Pose Regression with Feature Synthesis
Chen, S., Bhalgat, Y. S., Li, X., Bian, J.-W., Li, K., Wang, Z., & Prisacariu, V. A. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01983 · Cited by 70
“The original ‘GT’ poses are obtained using dSLAM [19] (green).”
Mahler, J., Patil, S., Kehoe, B., van den Berg, J., Ciocarlie, M., Abbeel, P., & Goldberg, K. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139882 · Cited by 70
“In practice M might be set based on the resolution of the sensor used to acquire measurements [29].”
BackgroundMethodInfluentialScene Understanding by Reasoning Stability and Safety
Zheng, B., Zhao, Y., Yu, J. C., Ikeuchi, K., & Zhu, S. C. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0795-4 · Cited by 70
Underwater 3D capture using a low-cost commercial depth camera
Digumarti, S. T., Chaurasia, G., Taneja, A., Siegwart, R., Thomas, A. F., & Beardsley, P. A. (2016) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2016.7477644 · Cited by 70
“Underwater 3D capture is being increasingly used in marine biology and oceanology; our approach offers exciting prospects for such applications.”
BackgroundLarge-scale and drift-free surface reconstruction using online subvolume registration
Fioraio, N., Taylor, J., Fitzgibbon, A. W., Stefano, L. D., & Izadi, S. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7299077 · Cited by 69
“Our proposal builds upon the successful KinectFusion framework [14, 10].”
BackgroundMethodSelf-citationLaser scan quality 3-D face modeling using a low-cost depth camera
Hernandez, M., Choi, J., & Medioni, G. G. (2012) · European Signal Processing Conference (EUSIPCO) · Cited by 69
On the performance of metrics to predict quality in point cloud representations
Ebrahimi, T., & Alexiou, E. (2017) · SPIE Applications of Digital Image Processing · doi:10.1117/12.2275142 · Cited by 69
Adversarial Texture Optimization From RGB-D Scans
Huang, J., Thies, J., Dai, A., Kundu, A., Jiang, C. M., Guibas, L. J., Nießner, M., & Funkhouser, T. A. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00163 · Cited by 69
“The wide availability of consumer range cameras has spurred extensive research in geometric reconstruction of real-world objects and scenes, with state-of-the-art 3D reconstruction approaches now providing robust camera tracking and 3D surface reconstruction [22, 19, 33, 9].”
BackgroundVS-Net: Voting with Segmentation for Visual Localization
Huang, Z., Zhou, H., Li, Y., Yang, B., Xu, Y., Zhou, X., Bao, H., Zhang, G., & Li, H. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00604 · Cited by 68
GRAMMAR-SUPPORTED 3D INDOOR RECONSTRUCTION FROM POINT CLOUDS FOR “AS-BUILT” BIM
Becker, S., Peter, M., & Fritsch, D. (2015) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-ii-3-w4-17-2015 · Cited by 68
Photorealistic rendering of mixed reality scenes
Kronander, J., Banterle, F., Gardner, A., Miandji, E., & Unger, J. (2015) · Computer Graphics Forum · doi:10.1111/cgf.12591 · Cited by 68
A Survey on Human Performance Capture and Animation
Xia, S., Gao, L., Lai, Y., Yuan, M., & Chai, J. (2017) · Journal of Computer Science and Technology · doi:10.1007/s11390-017-1742-y · Cited by 69
“[8] proposed a system named KinectFusion that can acquire complex models accurately in real time with only a single Kinect.”
BackgroundMassiceti, D., Hicks, S. L., & van Rheede, J. J. (2018) · PLOS ONE · doi:10.1371/journal.pone.0199389 · Cited by 54
“Extending this, recent years have seen the proliferation of methods for the fusion of global 3D maps of environments [65, 66, 105–107].”
Hammady, R., Ma, M., & Powell, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-95282-6_26 · Cited by 68
“3 of tracking research conducted with the monocular camera [18] [10] or with Kinect cameras [19] in order to track complex 3D models in real-time while avoiding occlusion and illumination [15].”
Background3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation
Moschoglou, S., Ploumpis, S., Nicolaou, M. A., Papaioannou, A., & Zafeiriou, S. P. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-020-01329-8 · Cited by 68
“Moreover, the low quality database was captured with a KinectFusion framework (Newcombe et al. 2011).”
MethodSupervoxel Convolution for Online 3D Semantic Segmentation
Huang, S.-S., Ma, Z., Mu, T., Fu, H., & Hu, S. (2021) · ACM Transactions on Graphics · doi:10.1145/3453485 · Cited by 68
Object Detection and Pose Tracking for Augmented Reality: Recent Approaches
Uchiyama, H., & Marchand, É. (2012) · HAL · Cited by 67
A Novel Method for the Extrinsic Calibration of a 2D Laser Rangefinder and a Camera
Dong, W., & Isler, V. (2018) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2819082 · Cited by 67
A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction
Kühn, A., Hirschmüller, H., Scharstein, D., & Mayer, H. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-016-0946-x · Cited by 67
“Local methods, on the other hand, yield better scalability (Fuhrmann and Goesele 2011) and runtime performance (Newcombe et al. 2011; Steinbrücker et al. 2013).”
MethodC-blox: A Scalable and Consistent TSDF-based Dense Mapping Approach
Millane, A., Taylor, Z., Oleynikova, H., Nieto, J. I., Siegwart, R., & Cadena, C. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593427 · Cited by 67
“Recently, the commodification of depth cameras has seen impressive results produced in the field of dense 3D reconstruction from visual sensors [4], [5].”
BackgroundMethodInfluentialReconstructing scenes with mirror and glass surfaces
Whelan, T. J., Goesele, M., Lovegrove, S. J., Straub, J., Green, S., Szeliski, R., Butterfield, S., Verma, S., & Newcombe, R. A. (2018) · ACM Transactions on Graphics · doi:10.1145/3197517.3201319 · Cited by 67
“Since no modification to the scanning and reconstruction system is necessary, we refer the reader to the literature on KinectFusion and follow-up publications for details and related work [Kähler et al. 2015; Newcombe et al. 2011; Nießner et al. 2013].”
MethodSelf-citationLeast Squares Optimization: From Theory to Practice
Grisetti, G., Guadagnino, T., Aloise, I., Colosi, M., Corte, B. D., & Schlegel, D. (2020) · Robotics · doi:10.3390/robotics9030051 · Cited by 67
DART: dense articulated real-time tracking with consumer depth cameras
Schmidt, T., Newcombe, R. A., & Fox, D. (2015) · Autonomous Robots · doi:10.1007/s10514-015-9462-z · Cited by 67
“Alternatively, the SDF functions could easily be generated from real-world objects for which no model is readily available using an efficient 3D scanning method, such as those developed by Newcombe et al. (2011), Sturm et al. (2013), or Henry et al. (2013).”
BackgroundMethodSelf-citationVirtual Mirror Rendering With Stationary RGB-D Cameras and Stored 3-D Background
Shen, J., Su, P.-C., Cheung, S.-C. S., & Zhao, J. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2268941 · Cited by 66
“6(a) shows a virtual view of a wall rendered from a 3-D structure created by applying the ICP algorithm from [10] to align Fig.”
InfluentialAdaGrasp: Learning an Adaptive Gripper-Aware Grasping Policy
Xu, Z., Qi, B., Agrawal, S., & Song, S. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9560833 · Cited by 66
“The gripper geometry is captured by 10 depth images and encoded as a 3D TSDF volume [25].”
MethodTruncated Signed Distance Function: Experiments on Voxel Size
Werner, D., Al-Hamadi, A. K., & Werner, P. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-11755-3_40 · Cited by 66
The Semantic Paintbrush: Interactive 3D Mapping and Recognition in Large Outdoor Spaces
Miksik, O., Vineet, V., Lidegaard, M., Prasaath, R., Nießner, M., Golodetz, S., Hicks, S. L., Pérez, P., Izadi, S., & Torr, P. H. S. (2015) · Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems · doi:10.1145/2702123.2702222 · Cited by 57
“• Extensions to KinectFusion [22] to support visual odometry for pose estimation alongside stereo data input.”
BackgroundSelf-citationSimulating Kinect Infrared and Depth Images
Landau, M., Choo, B. Y., & Beling, P. A. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2494877 · Cited by 66
“Furthermore, the online resources listed as well as many other available data sets do not include a model of the recorded object, and the user is left to find a CAD model of a related object close in shape and size, or use a 3-D object scanning method [8] to generate a less than perfect model.”
BackgroundDesign of parallel-jaw gripper tip surfaces for robust grasping
Guo, M., Gealy, D. V., Liang, J., Mahler, J., Goncalves, A., McKinley, S., Ojea, J. A., & Goldberg, K. Y. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989330 · Cited by 67
“Registration was performed using convolutional neural networks for a coarse pose estimate [36] and Iterated Closest Point matching with a weighted point-to-plane objective [37] for fine pose estimation in the plane of the table.”
A Multi-Modal, Discriminative and Spatially Invariant CNN for RGB-D Object Labeling
Asif, U., Bennamoun, M., & Sohel, F. A. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2747134 · Cited by 66
“, [1]), have increased the demand for the generation of models for the understanding of indoor environments at the object- and scene-levels.”
BackgroundiMapper: interaction-guided scene mapping from monocular videos
Monszpart, Á., Guerrero, P., Ceylan, D., Yumer, E., & Mitra, N. J. (2019) · ACM Transactions on Graphics · doi:10.1145/3306346.3322961 · Cited by 66
“On the one hand, scene estimation methods such as Kinect Fusion [Newcombe et al. 2011] and Bundle Fusion [Dai et al.”
MethodOmniKinect: real-time dense volumetric data acquisition and applications
Kainz, B., Hauswiesner, S., Reitmayr, G., Steinberger, M., Grasset, R., Gruber, L., Veas, E. E., Kalkofen, D., Seichter, H., & Schmalstieg, D. (2012) · ACM Symposium on Virtual Reality Software and Technology (VRST) · doi:10.1145/2407336.2407342 · Cited by 65
“The KinectFusion range covers tests with TSDF volume sizes between 1283 and 2563 .”
BackgroundMethodInfluentialWeber, T., Hänsch, R., & Hellwich, O. (2015) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2014.12.014 · Cited by 65
CopyMe3D: Scanning and Printing Persons in 3D
Sturm, J., Bylow, E., Kahl, F., & Cremers, D. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40602-7_43 · Cited by 64
“On the other hand, the advent of consumer depth sensors such as the Microsoft Kinect has led to novel approaches to 3D camera tracking and reconstruction [5, 10, 19].”
BackgroundMethodInfluentialSLAMesh: Real-time LiDAR Simultaneous Localization and Meshing
Ruan, J., Li, B., Wang, Y., & Sun, Y. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161425 · Cited by 64
Active exploration using trajectory optimization for robotic grasping in the presence of occlusions
Kahn, G., Sujan, P., Patil, S., Bopardikar, S. D., Ryde, J., Goldberg, K., & Abbeel, P. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139864 · Cited by 64
“With the recent trend of miniaturization of depth sensors [13], [14], [27], one can envision mounting these miniature sensors on the palms and wrists of end-effectors to gain a better understanding of the 3D world for reliable grasping and manipulation.”
BackgroundStereo vision and IMU based real-time ego-motion and depth image computation on a handheld device
Schmid, K., & Hirschmüller, H. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631242 · Cited by 64
“Modern approaches aim at matching all pixels, which require graphic card implementations due to the high computational load [4] and partly rely on active sensors [5], [6] that do not work outdoors due to sunlight.”
BackgroundAdaptive pulsed laser line extraction for terrain reconstruction using a dynamic vision sensor
Brändli, C., Mantel, T., Hutter, M., Hoepflinger, M. A., Berner, R., Siegwart, R., & Delbrück, T. (2014) · Frontiers in Neuroscience · doi:10.3389/fnins.2013.00275 · Cited by 64
Acoustic Classification and Optimization for Multi-Modal Rendering of Real-World Scenes
Schissler, C., Loftin, C., & Manocha, D. (2017) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2017.2666150 · Cited by 64
“The Iterative Closest Point algorithm [32] aligns the depth image for a given frame with the structure of previously captured data, while Structure from Motion approaches match feature points (e.g., SIFT) in the images to estimate the camera poses.”
MethodDistributed stereo vision‐based 6D localization and mapping for multi‐robot teams
Schuster, M. J., Schmid, K., Brand, C., & Beetz, M. (2018) · Journal of Field Robotics · doi:10.1002/rob.21812 · Cited by 64
“It can, for example, be approached by using image features as identifiable landmarks (Endres et al., 2012), by matching visual keyframes (Leishman, McLain, & Beard, 2013) or through the registration of depth data (Newcombe et al., 2011).”
BackgroundMethodROLS : Robust Object-Level SLAM for Grape Counting
Nellithimaru, A., & Kantor, G. A. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00321 · Cited by 65
“It fuses instance segmentation with Truncated Signed Distance Functions (TSDF) presented in Kinect Fusion [14].”
MethodFutureMapping 2: Gaussian Belief Propagation for Spatial AIPreprint
Davison, A. J., & Ortiz, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.14139 · Cited by 65
“For instance, in dense SLAM data associate (such as the ICP tracking in KinectFusion [28]), each pixel measurement from a depth camera is associated with several possible locations in a dense model, and this association is refined iteratively through ICP.”
MethodSelf-citationCAVBench: A Benchmark Suite for Connected and Autonomous Vehicles
Wang, Y., Liu, S., Wu, X., & Shi, W. (2018) · 2018 IEEE/ACM Symposium on Edge Computing (SEC) · doi:10.1109/sec.2018.00010 · Cited by 63
A Survey of Visual SLAM Methods
Sahili, A. R., Hassan, S. A., Sakhrieh, S., Mounsef, J., Maalouf, N., Arain, B., & Taha, T. (2023) · IEEE Access · doi:10.1109/access.2023.3341489 · Cited by 63
“Examples of the direct methods include KinectFusion [9], RGBDTAM [10], and ID-RGBDO [11], which can estimate the camera motion either by using the frame-to-model mechanisms or by using the most informative points in the camera frame.”
MethodBleser, G., Damen, D., Behera, A., Hendeby, G., Mura, K., Miezal, M., Gee, A. P., Petersen, N., Maçães, G., Domingues, H., et al. (2015) · PLoS ONE · doi:10.1371/journal.pone.0127769 · Cited by 63
“[55], although appearance information is incorporated.”
Handling occlusions in augmented reality based on 3D reconstruction method
Tian, Y., Long, Y., Xia, D., Yao, H., & Zhang, J. (2015) · Neurocomputing · doi:10.1016/j.neucom.2014.12.081 · Cited by 63
Learning hierarchical sparse features for RGB-(D) object recognition
Bo, L., Ren, X., & Fox, D. (2014) · The International Journal of Robotics Research · doi:10.1177/0278364913514283 · Cited by 63
“For instance, the Microsoft Kinect sensor, developed by Prime-Sense, provides 640 × 480 color and depth images at 30 frames per second and has been successfully used for computer gaming (Shotton et al., 2011) and 3D reconstruction (Henry et al., 2010; Newcombe et al., 2011).”
MethodPreclinical usability study of multiple augmented reality concepts for K-wire placement
Fischer, M., Fuerst, B., Lee, S. C., Fotouhi, J., Habert, S., Weidert, S., Euler, E., Osgood, G. M., & Navab, N. (2016) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-016-1363-x · Cited by 63
Simultaneous Localization and Appearance Estimation with a Consumer RGB-D Camera
Wu, H., Wang, Z., & Zhou, K. (2015) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2015.2498617 · Cited by 63
Representation, Analysis, and Recognition of 3D Humans: A Survey
Berretti, S., Daoudi, M., Turaga, P. K., & Basu, A. (2018) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3182179 · Cited by 63
“[112] presented the Kinect Fusion system that operates on live depth data coming from a moving Kinect camera, and creates a highquality 3D model of a scene.”
BackgroundNeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Cameras
Suo, X., Jiang, Y., Lin, P., Zhang, Y., Wu, M., Guo, K., & Xu, L. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00616 · Cited by 63
Comparison of modern open-source Visual SLAM approaches
Sharafutdinov, D., Griguletskii, M., Kopanev, P., Kurenkov, M., Ferrer, G., Бурков, А. В., Gonnochenko, A., & Tsetserukou, D. (2023) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-023-01812-7 · Cited by 64
Camera, LiDAR and Multi-modal SLAM Systems for Autonomous Ground Vehicles: a Survey
Chghaf, M., Rodríguez, S., & Elouardi, A. (2022) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-022-01582-8 · Cited by 62
“RGB-D Camera Methods KinectFusion [87] was the first method to use RGB-D camera to construct dense 3D depth maps for tracking and mapping.”
MethodIntegrating depth and color cues for dense multi-resolution scene mapping using RGB-D cameras
Stückler, J., & Behnke, S. (2012) · IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI) · doi:10.1109/mfi.2012.6343050 · Cited by 62
Anwer, A., Ali, S. S. A., Khan, A., & Mériaudeau, F. (2017) · IEEE Access · doi:10.1109/access.2017.2733003 · Cited by 62
“environment utilizes the Kinect Fusion algorithm [27], [28] using the Kinect SDK due to its extensive support for the KinectToF sensor.”
MethodTowards Fully Mobile 3D Face, Body, and Environment Capture Using Only Head-worn Cameras
Cha, Y.-W., Price, T., Wei, Z., Lu, X., Rewkowski, N., Chabra, R., Qin, Z., Kim, H., Su, Z., Liu, Y., et al. (2018) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2018.2868527 · Cited by 62
Gesture Recognition Based on CNN and DCGAN for Calculation and Text Output
Fang, W., Ding, Y., Zhang, F., & Sheng, J. (2019) · IEEE Access · doi:10.1109/access.2019.2901930 · Cited by 62
PIRVS: An Advanced Visual-Inertial SLAM System with Flexible Sensor Fusion and Hardware Co-Design
Zhang, Z., Liu, S., Tsai, G., Hu, H., Chu, C.-C., & Zheng, F. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460672 · Cited by 62
Hierarchical Topic Model Based Object Association for Semantic SLAM
Zhang, J., Gui, M., Wang, Q., Liu, R., Xu, J., & Chen, S. (2019) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2019.2932216 · Cited by 62
“The previous SLAM techniques rely on low-level landmarks, such as points [19, 33], lines [10, 23] and surface patches [21, 24].”
MethodNeuralHOFusion: Neural Volumetric Rendering under Human-object Interactions
Jiang, Y., Jiang, S., Sun, G., Su, Z., Guo, K., Wu, M., Yu, J., & Xu, L. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00606 · Cited by 62
“Besides, the low-end fusion approaches [34, 43, 44, 57, 63] adopt the most handy monocular setup with a temporal fusion pipeline [35], but suffer from the inherent self-occlusion constraint.”
MethodFrom Capture to Display: A Survey on Volumetric VideoPreprint
Jin, Y., Hu, K., Liu, J., Wang, F., & Liu, X. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.05658 · Cited by 62
“The depth map is transformed into the coordinate system of the color image, and the depth values are assigned to corresponding pixels in the color image, resulting in aligned RGB-D images where each pixel contains both color and depth information [109].”
BackgroundDense RGB-D-inertial SLAM with map deformations
Laidlow, T., Bloesch, M., Li, W., & Leutenegger, S. (2017) · 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206591 · Cited by 61
“RGB-D SLAM approaches that make use of depth cameras include KinectFusion [16] and other methods employing signed distance function-based volumetric mapping, such as [17]–[19].”
MethodTian, F., Gao, Y., Fang, Z., Fang, Y., Gu, J., Fujita, H., & Hwang, J. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3080928 · Cited by 61
Wang, K., Zhao, G., & Lǚ, J. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3379993 · Cited by 61
“In the past, real-time dense mapping methods [60], [61], [62] have been developed, but most of the previous methods suffer from high computational cost, monotonous application scenarios, or low scalability.”
MethodVisual industrial inspection using aerial robots
Omari, S., Gohl, P., Burri, M., Achtelik, M., & Siegwart, R. (2014) · International Conference on Applied Robotics for the Power Industry (CARPI) · doi:10.1109/carpi.2014.7030056 · Cited by 61
“Lastly, we evaluate the navigation system in a set of experiments.”
Method
Metadata
- Authors
- Newcombe, R. A., Fitzgibbon, A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A. J., Kohi, P., Shotton, J., & Hodges, S.
- Affiliations
- Imperial College London (GB)
- Microsoft (United States) (US)
- Venue
- 2011 10th IEEE International Symposium on Mixed and Augmented Reality
- Publisher
- IEEE
- Published
- 2011-10
- Pages
- 127-136
- ISSN
- 1554-7868 (ISSN-L)
- OpenAlex
- W1987648924
- Cited by
- 4,008
- References
- 34
- Citations by year
- 2026: 120 · 2025: 200 · 2024: 213 · 2023: 252 · 2022: 231 · 2021: 299 · 2020: 314 · 2019: 357 · 2018: 383 · 2017: 361 · 2016: 322 · 2015: 343 · 2014: 256 · 2013: 243 · 2012: 112
- FWCI
- 378.08
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR (publishedVersion)
- Lancaster EPrints (Lancaster University) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Keywords
- KinectFusion, real-time 3D reconstruction, depth camera, Kinect sensor, iterative closest point, pose tracking, indoor scene reconstruction, augmented reality, GPU rendering
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.