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 901–1,000 of 1,006
ILabel: Interactive Neural Scene LabellingPreprint
Zhi, S., Sucar, E., Mouton, A., Haughton, I., Laidlow, T., & Davison, A. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.14637 · Cited by 44
“surfels, meshes and voxels) [8, 26, 28, 42] and more recently, to neural representations [3], increasingly involving semantics [20, 25, 32, 38, 40, 44, 45].”
BackgroundSelf-citationPOCD: Probabilistic Object-Level Change Detection and Volumetric Mapping in Semi-Static Scenes
Qian, J., Chatrath, V., Yang, J., Servos, J., Schoellig, A. P., & Waslander, S. L. (2022) · Robotics: Science and Systems · doi:10.15607/rss.2022.xviii.013 · Cited by 44
FarfetchFusion: Towards Fully Mobile Live 3D Telepresence Platform
Lee, K., Yi, J., & Lee, Y. (2023) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3570361.3592525 · Cited by 43
“We design our system based on the concept of volumetric fusion, a representative 3D reconstruction approach that generates realistic and smooth surfaces from multiview RGB-D inputs (e.g., KinectFusion [40] and its variants [24, 39, 41]).”
MethodInfluentialFrom 3D Sensing to Printing: A Survey
Zhang, L., Dong, H., & Saddik, A. E. (2015) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/2818710 · Cited by 43
“…has several advantages: (1) it enables the use of portable 3D sensors to scan large objects or scenes conveniently without complex configurations [Newcombe et al. 2011]; (2) the operating steps can be easily understood and conducted by common consumers, which facilitates commercialization and…”
BackgroundPre-touch sensing for sequential manipulation
Yang, B., Lancaster, P., & Smith, J. R. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989594 · Cited by 43
“We used Kinect Fusion [23] to create each reference model, and the PCL library’s ICP algorithm [24] to do the matching.”
MethodScaling CNNs for High Resolution Volumetric Reconstruction from a Single Image
Johnston, A., Garg, R., Carneiro, G., Reid, I. D., & van den Hengel, A. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.114 · Cited by 43
“Systems like KinectFusion [25] and DynamicFusion [24] have opened the possibilities for various applications in the field of augmented and virtual reality by providing high quality reconstruction with the help of cheap sensors like Kinect.”
BackgroundSurfel-Based Next Best View Planning
Monica, R., & Aleotti, J. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2852778 · Cited by 43
“[4] R. A. Newcombe et al., “KinectFusion: Real-time dense surface mapping and tracking,” in Proc.”
BackgroundInfluentialTowards additive manufacturing oriented geometric modeling using implicit functions
Li, Q., Hong, Q., Qi, Q., Ma, X., Han, X., & Tian, J. (2018) · Visual Computing for Industry Biomedicine and Art · doi:10.1186/s42492-018-0009-y · Cited by 43
PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction
Shi, Y., Xu, K., Nießner, M., Rusinkiewicz, S. M., & Funkhouser, T. A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01237-3_46 · Cited by 43
Autonomous navigation for UAVs managing motion and sensing uncertainty
González-Sieira, A., Cores, D., Mucientes, M., & Bugarín, A. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103455 · Cited by 43
“com/product-astra-pro KinectFusion [36] was used to obtain a dense 3D model from the data gathered with the RGB-D camera during the flight.”
MethodInfluentialLarge-Scale Volumetric Scene Reconstruction using LiDAR
Kühner, T., & Kümmerle, J. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197388 · Cited by 43
“In a first step correspondences are found by projecting all source points into the sensor model using the model described in chapter II-B and the corresponding target points are determined by raytracing the world model as done in [15].”
MethodA Sparse Gaussian Approach to Region-Based 6DoF Object Tracking
Stoiber, M., Pfanne, M., Strobl, K. H., Triebel, R., & Albu‐Schäffer, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69532-3_40 · Cited by 43
“Another recent development are methods that use depth cameras [13–16], which provide good results but depend heavily on depth image quality.”
MethodAgha, H., Geng, Y., Ma, X., Avşar, D. I., Kizhakidathazhath, R., Zhang, Y., Tourani, A., Bavle, H., Sánchez-López, J. L., Voos, H., et al. (2022) · Light Science & Applications · doi:10.1038/s41377-022-01002-4 · Cited by 43
Meilland, M., Comport, A. I., & Rives, P. (2014) · Journal of Field Robotics · doi:10.1002/rob.21531 · Cited by 43
“The projection of an infrared pattern allows us to recover dense depthmaps in real-time and can be used in SLAM systems such as Audras, Comport, Meilland, and Rives (2011), Henry, Krainin, Herbst, Ren, and Fox (2010), and Newcombe et al. (2011a). In Spinello and Arras (2011), three sensors are used to reconstruct a la…”
MethodOmniMapper: A modular multimodal mapping framework
Trevor, A. J. B., Rogers, J. G., & Christensen, H. I. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907122 · Cited by 43
“Creating maps using hand-held RGB-D Cameras has recently become popular, with approaches such as RGB-D Mapping [18], RGB-D SLAM [14], and Kinect Fusion [26].”
MethodLarge-scale three-dimensional measurement via combining 3D scanner and laser rangefinder
Shi, J., Sun, Z., & Bai, S. (2015) · Applied Optics · doi:10.1364/ao.54.002814 · Cited by 43
“According to alignment strategies, these methods can be categorized into three types: surface geometries-based method [14,15], trackerbased method [16,17], and marker-based method [18].”
MethodFiltered pose graph for efficient kinect pose reconstruction
Plantard, P., Shum, H. P. H., & Multon, F. (2016) · Multimedia Tools and Applications · doi:10.1007/s11042-016-3546-4 · Cited by 43
“5D point clouds, and fusing them can generate a 3D mesh of the tracked object [29].”
BackgroundHenríquez, P., Matuszewski, B. J., Andreu, Y., Bastiani, L., Colantonio, S., Coppini, G., D’Acunto, M., Favilla, R., Germanese, D., Giorgi, D., et al. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2666545 · Cited by 43
“The implemented reconstruction approach is based on the Kinect fusion method [11].”
MethodFast and Accurate Point Cloud Registration using Trees of Gaussian MixturesPreprint
Eckart, B., Kim, K., & Kautz, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.02587 · Cited by 43
“…of aligning two or more point clouds by estimating the relative transformation between them, and it has been an essential part of many computer vision algorithms such as 3D object matching [1], localization and mapping [2], dense 3D reconstruction of a scene [3], and object pose estimation [4].”
LocNDF: Neural Distance Field Mapping for Robot Localization
Wiesmann, L., Guadagnino, T., Vizzo, I., Zimmerman, N., Pan, Y., Kuang, H., Behley, J., & Stachniss, C. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3291274 · Cited by 42
“tions [2], [26], or do feature-based matching [17], [41].”
BackgroundMethodDistribution-Aligned Diffusion for Human Mesh Recovery
Foo, L. G., Gong, J. L., Rahmani, H., & Liu, J. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00846 · Cited by 42
Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps
Cheng, C., Yu, S., Wang, Z., Zhou, Y., & Wang, H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02415 · Cited by 42
“Within this area, 3D scene representation has become a primary research focus, resulting in the development of numerous sparse [3, 16, 24, 25] and dense [26, 27, 42] representation methods, which advance localization accuracy.”
SurroundWeb: Mitigating Privacy Concerns in a 3D Web Browser
Vilk, J., Molnár, D., Livshits, B., Ofek, E., Rossbach, C. J., Moshchuk, A., Wang, H. J., & Gal, R. (2015) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp.2015.33 · Cited by 42
“• RQ3: Is there a difference in user perceived sensitivity between giving the relative locations of flat surfaces vs. just stating the dimensions of flat surfaces?”
BackgroundDense RGB-D visual odometry using inverse depth
Gutiérrez-Gómez, D., Mayol-Cuevas, W. W., & Guerrero, J. J. (2015) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2015.09.026 · Cited by 42
“One drawback of the original KinectFusion is its limitation to small workspaces, which was nevertheless solved in latter works by using a cyclical buffer to shift the volume as the camera explores the environment [3], [46].”
BackgroundMethodInfluentialEfficient 3D Scene Labeling Using Fields of Trees
Kähler, O., & Reid, I. D. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.380 · Cited by 42
“Finally our current system relies on a Kinect sensor and the KinectFusion system, but volumetric 3D scene representations can recently also be acquired with standard RGB cameras and DTAM [9].”
MethodInfluentialSparse-then-dense alignment-based 3D map reconstruction method for endoscopic capsule robots
Turan, M., Pılavci, Y. Y., Ganiyusufoglu, I., Araújo, H. J., Konukoğlu, E., & Sitti, M. (2017) · Machine Vision and Applications · doi:10.1007/s00138-017-0905-8 · Cited by 42
“The Brown-Conrady undistortion technique was applied to handle the radial distortions [28],[29].”
MethodThe need 4 speed in real-time dense visual tracking
Kowdle, A., Rhemann, C., Fanello, S., Tagliasacchi, A., Taylor, J., Davidson, P., Dou, M., Guo, K., Keskin, C., Khamis, S., et al. (2018) · ACM Transactions on Graphics · doi:10.1145/3272127.3275062 · Cited by 42
“7.2 Rigid fusion – [Newcombe et al. 2011] – Fig.”
InfluentialSelf-citationEfficient Learning on Point Clouds with Basis Point Sets
Prokudin, S., Lassner, C., & Romero, J. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00370 · Cited by 42
3D Object Reconstruction from Hand-Object Interactions
Tzionas, D., & Gall, J. (2015) · MPG.PuRe (Max Planck Society) · Cited by 42
A mapping of visual SLAM algorithms and their applications in augmented reality
Covolan, J. P. M., Sementille, A. C., & Sanches, S. R. R. (2020) · Symposium on Virtual and Augmented Reality (SVR) · doi:10.1109/svr51698.2020.00019 · Cited by 42
“com/science/article/pii/S107731421930058X [41] R.”
BackgroundSemantic Mapping for Mobile Robots in Indoor Scenes: A Survey
Han, X., Li, S., Wang, X., & Zhou, W. (2021) · Information · doi:10.3390/info12020092 · Cited by 42
“An object database, consisting of 3D models of instance, is prepared beforehand using KinectFusion [43], and then instances are recognized with Generalized Hough Transform based on Point Pair Features.”
MethodHandVoxNet++: 3D Hand Shape and Pose Estimation Using Voxel-Based Neural Networks
Malik, J. N., Shimada, S., Elhayek, A., Ali, S. A., Theobalt, C., Golyanik, V., & Stricker, D. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3122874 · Cited by 42
“The projective TSDF [47] is practically more feasible because the nearest surface point is calculated on the line of sight in the camera frame.”
BackgroundVIP-SLAM: An Efficient Tightly-Coupled RGB-D Visual Inertial Planar SLAM
Chen, D., Wang, S., Xie, W., Zhai, S., Wang, N., Bao, H., & Zhang, G. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812354 · Cited by 42
Probabilistic Volumetric Fusion for Dense Monocular SLAM
Rosinol, A., Leonard, J. J., & Carlone, L. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00311 · Cited by 42
“Most of the literature using volumetric representations have therefore focused on studying ways to obtain better depth maps, such as with post-processing techniques, or on the weighting function to be used when fusing the depths [5, 13, 14, 28].”
BackgroundReview of Visual Simultaneous Localization and Mapping Based on Deep Learning
Zhang, Y., Wu, Y., Tong, K., Chen, H., & Yuan, Y. (2023) · Remote Sensing · doi:10.3390/rs15112740 · Cited by 42
Data association for semantic world modeling from partial views
Wong, L. L. S., Kaelbling, L. P., & Lozano‐Pérez, T. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364914559754 · Cited by 42
Modern techniques and applications for real-time non-rigid registration
Bouaziz, S., Tagliasacchi, A., Li, H., & Pauly, M. V. (2016) · SIGGRAPH Asia Courses · doi:10.1145/2988458.2988490 · Cited by 42
“In order to aggregate multiple scans over time, different methods can be used [50, 51, 27].”
MethodGee, T., James, J., van der Mark, W., Delmas, P. J., & Gimel’farb, G. (2016) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2016.7804433 · Cited by 42
“Note that for the estimated pose to be accurate, it is assumpted that the stereo frames have been captured at a minimal rate of 30 fps [17].”
BackgroundUsing extended measurements and scene merging for efficient and robust point cloud registration
Serafin, J., & Grisetti, G. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.03.008 · Cited by 42
Seeing the World in a Bag of Chips
Park, J. J., Holynski, A., & Seitz, S. M. (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/cvpr42600.2020.00149 · Cited by 42
Removing Moving Objects from Point Cloud Scenes
Litomisky, K., & Bhanu, B. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40303-3_6 · Cited by 42
“Similarly, the Kinect Fusion work [10], which implements a real-time version of ICP that runs on CUDA-enabled GPUs, deals with moving objects implicitly by using a volumetric representation.”
MethodA Framework for the Volumetric Integration of Depth ImagesPreprint
Prisacariu, V. A., Kähler, O., Cheng, M., Ren, C. Y., Valentin, J. P. C., Torr, P. H. S., Reid, I. D., & Murray, D. W. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1410.0925 · Cited by 42
Neural 3D Video SynthesisPreprint
Li, T. (2024) · arXiv (Cornell University) · doi:10.57702/ybfkwxpc · Cited by 42
An integrated approach to visual perception of articulated objects
Martin-Martin, R., Hofer, S., & Brock, O. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487714 · Cited by 41
“Other methods [6, 17] build on top of KinectFusion [15].”
BackgroundMethodSpaceBeam: LiDAR-driven one-shot mmWave beam management
Woodford, T., Zhang, X., Chai, E., Sundaresan, K., & Khojastepour, A. (2021) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3458864.3466864 · Cited by 41
“Then we use the KinectFusion method to find the location of the surfaces based on the volumetric truncated signed distance function (TSDF), while reducing the effect of depth noise in individual images [27].”
MethodSun, S., Mielle, M., Lilienthal, A. J., & Magnusson, M. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802373 · Cited by 41
“Traditional SLAM systems have focused mainly on camera tracking [1] and geometric surface reconstruction [2].”
NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigation
Zeng, Y., Ren, H., Wang, S., Huang, J., & Cheng, H. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127466 · Cited by 41
“Then, based on the estimated depth image, we reconstruct the surroundings in real-time and build a local Truncated Signed Distance Function (TSDF) [40] to label the distance to the surface of the obstacles for each position in the environment.”
Food volume computation for self dietary assessment applications
Dehais, J., Shevchik, S. A., Diem, P., & Mougiakakou, S. G. (2013) · IEEE International Conference on Bioinformatics and Bioengineering (BIBE) · doi:10.1109/bibe.2013.6701615 · Cited by 41
“Ground truth was obtained using the Kinect Fusion algorithm, which is sufficiently accurate for verification purposes [12], [13].”
Method6D Relocalisation for RGBD Cameras Using Synthetic View Regression
Gee, A. P., & Mayol-Cuevas, W. W. (2012) · British Machine Vision Conference (BMVC) · doi:10.5244/c.26.113 · Cited by 41
De-noising, stabilizing and completing 3D reconstructions on-the-go using plane priors
Dzitsiuk, M., Sturm, J., Maier, R. L., Ma, L., & Cremers, D. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989457 · Cited by 41
“While existing 3D reconstruction algorithms [1]–[6] are mostly targeted at offline use of the resulting 3D models, many applications in robotics and AR gaming require that valid and dependable models exist already during model acquisition, e.”
BackgroundBlock assembly for global registration of building scans
Yan, F., Nan, L., & Wonka, P. (2016) · ACM Transactions on Graphics · doi:10.1145/2980179.2980241 · Cited by 41
“Based on pairwise registration, the KinectFusion technique and its variants [Newcombe et al. 2011; Izadi et al. 2011; Whelan et al. 2012; Roth and Vona 2012; Nießner et al. 2013], and many successive techniques [Chen et al.”
MethodNovel Low Cost 3D Surface Model Reconstruction System for Plant Phenotyping
Liu, S., Acosta‐Gamboa, L., Huang, X., & Lorence, A. (2017) · Journal of Imaging · doi:10.3390/jimaging3030039 · Cited by 41
Reconstruction-Based Pairwise Depth Dataset for Depth Image Enhancement Using CNN
Jeon, J., & Lee, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01270-0_26 · Cited by 41
“, ASUS Xtion [2] and Occipital Structure sensor [34], depth images can be easily captured and have been utilized for improving the performance of vision algorithms, such as 3D reconstruction [32, 33, 7], object recognition [3, 11], and semantic segmentation [26, 14, 39, 6].”
BackgroundMethodAugmented Reality Remote Collaboration with Dense Reconstruction
Zillner, J., Méndez, E., & Wägner, D. (2018) · IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct) · doi:10.1109/ismar-adjunct.2018.00028 · Cited by 41
“KinectFusion [5] and InfiniTAM [8] both created high-quality models using depth sensors.”
BackgroundSafe and Robust Mobile Robot Navigation in Uneven Indoor Environments
Wang, C., Wang, J., Li, C., Ho, D., Cheng, J., Yan, T., Meng, L., & Meng, M. Q. ‐. (2019) · Sensors · doi:10.3390/s19132993 · Cited by 41
“For example, KinectFusion [15] stimulates the development of a vision-based 3D SLAM with low cost RGB-D sensors.”
BackgroundMethodRadiometric Scene Decomposition: Scene Reflectance, Illumination, and Geometry from RGB-D Images
Lombardi, S., & Nishino, K. (2016) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2016.39 · Cited by 41
“We use the KinectFusion algorithm [6, 12] to combine multiple depth images into a triangle mesh that is used as the input geometry.”
MethodContext‐Aware Mixed Reality: A Learning‐Based Framework for Semantic‐Level Interaction
Chen, L., Tang, W., John, N., Wan, T.-R., & Zhang, J. J. (2019) · Computer graphics forum (Print) · doi:10.1111/cgf.13887 · Cited by 17
Innovative Mobile Manipulator Solution for Modern Flexible Manufacturing Processes
Outón, J. L., Villaverde, I., Herrero, H., Esnaola, U., & Sierra, B. (2019) · Sensors · doi:10.3390/s19245414 · Cited by 41
“Approaches using 3D mapping have been introduced to improve robustness in infrastructure-less navigation, using truncated signed distance functions in voxel maps [18] or multiresolution surfel maps [19].”
MethodDRM-SLAM: Towards dense reconstruction of monocular SLAM with scene depth fusion
Ye, X., Ji, X., Sun, B., Chen, S., Wang, Z., & Li, H. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.02.044 · Cited by 41
Deep Learning for Underwater Visual Odometry Estimation
Teixeira, B., Silva, H. M., Matos, A. C., & Silva, E. (2020) · IEEE Access · doi:10.1109/access.2020.2978406 · Cited by 41
“RGB-D SLAM techniques [59], [60] leverage the capabilities of emergent structured light-based RGB-D cameras, namely the ability to automatically acquire absolute scale of the environment.”
MethodOmnidirectional Depth Extension Networks
Cheng, X., Wang, P., Zhou, Y., Guan, C., & Yang, R. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197123 · Cited by 41
3D Reconstruction of Non-Rigid Plants and Sensor Data Fusion for Agriculture Phenotyping
Sampaio, G. S., da Silva, L. A., & Marengoni, M. (2021) · Sensors · doi:10.3390/s21124115 · Cited by 41
Estimating Surface Normals with Depth Image Gradients for Fast and Accurate Registration
Nakagawa, Y., Uchiyama, H., Nagahara, H., & Taniguchi, R.-I. (2015) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2015.80 · Cited by 41
“Consequently, online registration [15], reconstruction [13] and recognition [19] in the 3D space are actively studied again while 3D image processing itself has a long history and is well-introduced in some textbooks [7].”
BackgroundMulti-sensor surface analysis for robotic ironing
Li, Y., Hu, X., Xu, D., Yue, Y., Grinspun, E., & Allen, P. K. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487788 · Cited by 34
Learning Quadrangulated Patches for 3D Shape Parameterization and Completion
Sarkar, K., Varanasi, K., & Stricker, D. (2017) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00051 · Cited by 41
Kernel Cuts: Kernel and Spectral Clustering Meet Regularization
Tang, M., Marin, D., Ayed, I. B., & Boykov, Y. Y. (2018) · International Journal of Computer Vision · doi:10.1007/s11263-018-1115-1 · Cited by 41
“Depth sensor are widely used in vision for 3D modelling [37, 79], semantic segmentation [34,45,78,87], motion flow [44].”
MethodSantos, T. T., Koenigkan, L. V., Barbedo, J. G. A., & Rodrigues, G. C. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16220-1_18 · Cited by 41
“These RGB-D devices are camera-projector triangulation-based systems assembled in a single device, also using coded-light to infer pixel correspondences [16].”
BackgroundInfluentialRobotic ironing with 3D perception and force/torque feedback in household environments
Estevez, D., Victores, J. G., Fernandez-Fernandez, R., & Balaguer, C. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206556 · Cited by 40
“The pan and tilt degrees of freedom of the robot’s neck were used to move 1https://github.com/roboticslab-uc3m/textiles the camera while scanning the scene with the KinectFusion algorithm, to generate the disparity required by the algorithm.”
MethodInfluentialMonocular Visual-Inertial Odometry with Planar Regularities
Chen, C., Geneva, P., Peng, Y., Lee, W., & Huang, G. P. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160620 · Cited by 40
Decomposed Guided Dynamic Filters for Efficient RGB-Guided Depth Completion
Wang, Y., Mao, Y., Liu, Q., & Dai, Y. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3292398 · Cited by 40
“D ENSE and accurate depth is essential for various applications, such as obstacle avoidance [1], virtual reality [2], and autonomous driving [3].”
BackgroundGSFusion: Online RGB-D Mapping Where Gaussian Splatting Meets TSDF Fusion
Wei, J., & Leutenegger, S. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3502065 · Cited by 41
“Once allocation is completed, the integration of measurements is carried out in the same manner as Kinect-Fusion [2].”
BackgroundMethodOKVIS2-X: Open Keyframe-Based Visual-Inertial SLAM Configurable With Dense Depth or LiDAR, and GNSS
Boche, S., Jung, J., Laina, S. B., & Leutenegger, S. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3619051 · Cited by 21
“Toaddressthislimitation,thecommunityhasproposedsystems thatcanleveragevisualdepthinformation[6],[7],[8]orLiDAR information [9], [10], [11] to build denser maps that can then be reused for downstream tasks—thereby naturally increasing memory requirements.”
Robust Instance Recognition in Presence of Occlusion and Clutter
Bonde, U., Badrinarayanan, V., & Cipolla, R. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10605-2_34 · Cited by 40
“Recent development in 3D reconstruction [17] has made reliable shape information available in real time.”
BackgroundRepurposing the Microsoft Kinect for Windows v2 for external head motion tracking for brain PET
Noonan, P. J., Howard, J., Hallett, W. A., & Gunn, R. N. (2015) · Physics in Medicine and Biology · doi:10.1088/0031-9155/60/22/8753 · Cited by 40
Edge Snapping-Based Depth Enhancement for Dynamic Occlusion Handling in Augmented Reality
Du, C., Chen, Y., Ye, M., & Ren, L. (2016) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2016.17 · Cited by 40
Fast Detection of Tomato Peduncle Using Point Cloud with a Harvesting Robot
Yoshida, T., Fukao, T., & Hasegawa, T. (2018) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2018.p0180 · Cited by 40
3-D Deep Feature Construction for Mobile Laser Scanning Point Cloud Registration
Zhang, Z., Sun, L., Zhong, R., Chen, D., Xu, Z., Wang, C., Qin, C., Sun, H., & Li, R. (2019) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2019.2910546 · Cited by 40
“To test the effects of different voxelization methods, we used the TDF, TSDF, and projective TSDF to perform the experiments.”
MethodLearning Non-Volumetric Depth Fusion Using Successive Reprojections
Donné, S., & Geiger, A. (2019) · 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.2019.00782 · Cited by 40
“[39] and KinectFusion [26], fusing various depth maps into a single truncated signed distance field (TSDF).”
BackgroundJoint Texture and Geometry Optimization for RGB-D Reconstruction
Fu, Y., Yan, Q., Liao, J., & Xiao, C. (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/cvpr42600.2020.00599 · Cited by 40
“(a) and (g) are the texture and geometry result by KinectFusion [23].”
BackgroundMethodA Semantic Slam-Based Dense Mapping Approach for Large-Scale Dynamic Outdoor Environment
Yang, L., & Wang, L. (2022) · Measurement · doi:10.1016/j.measurement.2022.112001 · Cited by 40
Fast and Accurate Registration of Structured Point Clouds with Small Overlaps
Ma, Y., Guo, Y., Zhao, J. C., Lu, M., Zhang, J., & Wan, J. (2016) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.86 · Cited by 40
Direct visual SLAM fusing proprioception for a humanoid robot
Scona, R., Nobili, S., Pétillot, Y., & Fallon, M. F. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8205943 · Cited by 40
“KinectFusion [12] was a seminal contribution to dense RGB-D SLAM.”
BackgroundExploring Extended Reality with ILLIXR: A New Playground for Architecture ResearchPreprint
Huzaifa, M., Desai, R., Grayson, S., Jiang, X., Jing, Y., Lee, J., Lu, F., Pang, Y., Ravichandran, J., Sinclair, F., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.04643 · Cited by 40
“For scene reconstruction, we chose KinectFusion [83] and ElasticFusion [121], two dense SLAM algorithms that use an RGB-Depth (RGB-D) camera to build a dense 3D map of the world.”
MethodGe, Y., Guo, B., Zha, P., Jiang, S., Jiang, Z., & Li, D. (2024) · Remote Sensing · doi:10.3390/rs16030473 · Cited by 39
“The literature [28] leverages images from multiple viewpoints, combines scene geometry constraints and estimates depths for sparse points to achieve high-quality dense reconstruction.”
BackgroundMaGS: Reconstructing and Simulating Dynamic 3D Objects with Mesh-Adsorbed Gaussian Splatting
Ma, S., Luo, Y., Yi, Y., & Yang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00818 · Cited by 39
“We render the median depths of the 3D Gaussians at T = 0 across 100 view-points, fuse them via TSDF, and reconstruct the initial mesh via TSDF Integration [37].”
Real-Time Metric-Semantic Mapping for Autonomous Navigation in Outdoor Environments
Jiao, J., Geng, R., Li, Y., Ren, X., Yang, B., Wu, J., Wang, L., Liu, M., Fan, R., & Kanoulas, D. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3429280 · Cited by 40
“This section reviews the current literature on mapping and navigation techniques, focusing specifically on algorithms developed for mobile robots in unstructured environments.”
Ahmadabadian, A. H., Sargeant, B., Erfani, T., Stuart Robson, A., Shortis, M. R., Hess, M., & Boehm, J. (2014) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.04.001 · Cited by 39
Tracking an RGB-D Camera Using Points and Planes
Ataer-Cansızoğlu, E., Taguchi, Y., Ramalingam, S., & Garaas, T. W. (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.14 · Cited by 39
“KinectFusion [13] extended commonly used frame-to-frame ICP registration to frame-tomodel ICP registration: The system accumulated registered point clouds in a truncated signed distance function (TSDF) volume [6] and generated a virtual depth map, which has much less noise, to be registered to the current depth map.”
BackgroundMethodDynamic 2D/3D registration for the Kinect
Bouaziz, S., & Pauly, M. V. (2013) · ACM SIGGRAPH Courses · doi:10.1145/2504435.2504456 · Cited by 39
Simultaneous Localization and Calibration: Self-Calibration of Consumer Depth Cameras
Zhou, Q.-Y., & Koltun, V. (2014) · 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.2014.65 · Cited by 39
Xiao, J., Zhou, Y., & Zhou, Z. (2015) · Scientia Sinica Informationis · doi:10.1360/n112014-00076 · Cited by 39
Wu, M.-L., Chien, J.-C., Wu, C., & Lee, J.-D. (2018) · Sensors · doi:10.3390/s18082505 · Cited by 39
“i s 10 S, i cl es a an a P , and has a display resolution of 1280 i l ( i l i t l s ti l i i (Simultaneous Localization and Mapping) [31,32] to pr cess spatial projections [33], and allows the user to access the u er interface in the augmented reali y environment through voice and gestures.”
BackgroundMethodMuglikar, M., Zhang, Z., & Scaramuzza, D. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197357 · Cited by 39
“, Truncated Signed Distance Field in [6], surfels in [7]), little work has been done exploring alternative map representations for sparse SLAM.”
Li, M., Chen, R., Liao, X., Guo, B., Zhang, W., & Guo, G. (2020) · Remote Sensing · doi:10.3390/rs12050869 · Cited by 39
“In [30–35], a variety of visual SLAM schemes were proposed.”
BackgroundHu, Y.-T., Wang, J., Yeh, R. A., & Schwing, A. G. (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/cvpr46437.2021.00147 · Cited by 39
“Multiple-View Object Shape Reconstruction: 3D understanding using multiple images has been studied and used for depth estimation [34, 74], scene reconstruction [51], semantic segmentation for 3D scenes [38], 3D object detection [9, 50, 68], and 3D object reconstruction [12, 85].”
MethodMotion planning in dynamic environments using context-aware human trajectory prediction
Finean, M. N., Petrović, L., Merkt, W., Marković, I., & Havoutis, I. (2023) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2023.104450 · Cited by 40
Augmented Reality 3D Discrepancy Check in Industrial Applications
Wasenmüller, O., Meyer, M., & Stricker, D. (2016) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2016.15 · Cited by 39
“Following the works of [24, 29], the surface is stored implicitly as a truncated signed distance function in a 3D volume approximated by a finite number of voxels.”
MethodInfluentialModeling hair from an RGB-D camera
Zhang, M., Wu, P., Wu, H., Weng, Y., Zheng, Y., & Zhou, K. (2018) · ACM Transactions on Graphics · doi:10.1145/3272127.3275039 · Cited by 39
Real-time mesh-based scene estimation for aerial inspection
Teixeira, L., & Chli, M. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759714 · Cited by 39
Aggressive Deep Driving: Model Predictive Control with a CNN Cost ModelPreprint
Drews, P., Williams, G., Goldfain, B., Theodorou, E. A., & Rehg, J. M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.05303 · Cited by 39
“There are many SLAM approaches that use cameras [8, 9], LIDAR [10], or other sensor combinations [11] to provide accurate position.”
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.