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 201–300 of 1,006
Accelerated Coordinate Encoding: Learning to Relocalize in Minutes Using RGB and Poses
Brachmann, E., Cavallari, T., & Prisacariu, V. A. (2023) · 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/cvpr52729.2023.00488 · Cited by 206
Live Metric 3D Reconstruction on Mobile Phones
Tanskanen, P., Kolev, K., Meier, L., Camposeco, F., Saurer, O., & Pollefeys, M. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.15 · Cited by 201
“Impressive results were obtained with video cameras [7] and depth sensors [15, 8].”
BackgroundMotion removal for reliable RGB-D SLAM in dynamic environments
Sun, Y., Liu, M., & Meng, M. Q.-H. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.07.002 · Cited by 201
Incremental dense semantic stereo fusion for large-scale semantic scene reconstruction
Vineet, V., Miksik, O., Lidegaard, M., Niebner, M., Golodetz, S., Prisacariu, V. A., Kahler, O., Murray, D. W., Izadi, S., Peerez, P., et al. (2015) · 2015 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2015.7138983 · Cited by 200
“KinectFusion [20] directly sensed depth using active sensors and fused noisy depth measurements of the perceived scene over time to recover high-quality surfaces, but suffered from the same scalability issue.”
BackgroundMethodInfluentialSelf-citationVirtual Replicas for Remote Assistance in Virtual and Augmented Reality
Oda, O., Elvezio, C., Sukan, M., Feiner, S., & Tversky, B. (2015) · Proceedings of the 28th Annual ACM Symposium on User Interface Software & Technology · doi:10.1145/2807442.2807497 · Cited by 200
“When that is not feasible, a dynamic scene reconstruction algorithm could be used (e.g., [15, 27, 9, 5]).”
BackgroundMethodDetailed Full-Body Reconstructions of Moving People from Monocular RGB-D Sequences
Bogo, F., Black, M. J., Loper, M., & Romero, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.265 · Cited by 200
“Model-free systems like KinectFusion [18, 26] create detailed 3D reconstructions of rigid scenes, including high-quality appearance models [38], in real time from a moving RGB-D sensor.”
Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis
Zhang, Z., Sattler, T., & Scaramuzza, D. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-020-01399-8 · Cited by 201
Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey
Tang, Y. S., Zhao, C., Wang, J., Zhang, C., Sun, Q., Zheng, W. X., Du, W., Qian, F., & Kurths, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3167688 · Cited by 212
“Meanwhile, dense maps are usually constructed by direct methods based on RGB-D sensors, like [44], [45], and [77].”
MethodMori, S., Ikeda, S., & Saito, H. (2017) · IPSJ Transactions on Computer Vision and Applications · doi:10.1186/s41074-017-0028-1 · Cited by 179
“vSLAM systems such as PTAM [55] and KinectFusion [56] are a typical option for estimating the camera poses in an arbitrary environment [35, 36, 43].”
BackgroundReal-time RGB-D camera relocalization
Glocker, B., Izadi, S., Shotton, J., & Criminisi, A. (2013) · 2013 IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2013.6671777 · Cited by 195
“A KinectFusion system running at 30 FPS will continue to run at about 27 FPS when keyframe harvesting is running in the same computation thread.”
BackgroundMethodSelf-citation3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks
Zou, C., Yumer, E., Yang, J., Ceylan, D., & Hoiem, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.103 · Cited by 195
“We employ the idea of Gaussian Force Fields [6] and Truncated Signed Distance Function (TSDF) [29] to formulate the following continuously differentiable energy function which is convex in a large neighborhood of the parameters: Ep = − ∑ m,n Vpmin ( exp ( − ‖R(θ)Spm + T − qn‖ 2 σ2 ) , ξ ) , (1) where R(θ) is the rotat…”
MethodInfluentialWorld-stabilized annotations and virtual scene navigation for remote collaboration
Gauglitz, S., Nuernberger, B., Turk, M., & Höllerer, T. (2014) · Proceedings of the 27th annual ACM symposium on User interface software and technology · doi:10.1145/2642918.2647372 · Cited by 195
“Building upon a tetrahedralization of a sparse point cloud, the modeling approach taken here is very fast (as demonstrated above), but results in a model that does not exhibit the level of detail as achievable, for example, with dense volumetric fusion [9, 32, 35].”
BackgroundMethodPark, K., Mousavian, A., Xiang, Y., & Fox, D. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01072 · Cited by 152
AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network
Wei, Z., Zhu, Q., Min, C., Chen, Y., & Wang, G. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00613 · Cited by 194
Database‐Assisted Object Retrieval for Real‐Time 3D Reconstruction
Li, Y., Dai, A., Guibas, L., & Nießner, M. (2015) · Computer Graphics Forum · doi:10.1111/cgf.12573 · Cited by 193
3D Object Reconstruction from a Single Depth View with Adversarial Learning
Yang, B., Wen, H., Wang, S., Clark, R., Markham, A., & Trigoni, N. (2017) · 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw.2017.86 · Cited by 193
A Survey of Rigid 3D Pointcloud Registration Algorithms
Bellekens, B., Spruyt, V., Berkvens, R., & Weyn, M. (2014) · Ghent University Academic Bibliography (Ghent University) · Cited by 193
Time-of-Flight Cameras: Principles, Methods and Applications
Hansard, M., Lee, S., Choi, O., & Horaud, R. (2013) · SpringerBriefs in Computer Science · doi:10.1007/978-1-4471-4658-2 · Cited by 192
Additive Manufacturing Technology: Potential Implications for U.S. Manufacturing CompetitivenessPreprint
Ford, S. L. N. (2014) · SSRN Electronic Journal · Cited by 190
Autonomous Visual Navigation for Mobile Robots: A Systematic Literature Review
Yasuda, Y. D. V., Martins, L. E. G., & Cappabianco, F. A. M. (2020) · ACM Computing Surveys · doi:10.1145/3368961 · Cited by 190
“In the survey, they compared the implementation of SLAM methods based on extraction of features, which may use filters (MonoSLAM [31]) or bundle adjustment (PTAM [62]), with direct methods such as DTAM [90] (based on registration of images) and LSD-SLAM [36] (based on semi-dense visual odometry), and methods that use…”
MethodGCNv2: Efficient Correspondence Prediction for Real-Time SLAM
Tang, J., Ericson, L., Folkesson, J., & Jensfelt, P. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2927954 · Cited by 188
Structured Light-Based 3D Reconstruction System for Plants
Nguyen, T., Slaughter, D., Max, N., Maloof, J., & Sinha, N. (2015) · Sensors · doi:10.3390/s150818587 · Cited by 187
“In [11], the Kinect device was utilized to reconstruct dense indoor scenes.”
MethodCritical Design and Control Issues of Indoor Autonomous Mobile Robots: A Review
Niloy, M. A., Shama, A., Chakrabortty, R. K., Ryan, M. J., Badal, F. R., Tasneem, Z., Ahamed, M. H., Moyeen, S. I., Das, S. K., Ali, M. F., et al. (2021) · IEEE Access · doi:10.1109/access.2021.3062557 · Cited by 189
“Some used RGB-D sensors as the primary sensor such as Kinectfusion [173], Kintinuous [174], BAD-SLAM [175] etc. VSLAM is still very much an ongoing research topic, including incorporating the power of modern GPUs, to create a more dense map with semantic information and better tracking [78], [176], [177]], [178], [179…”
MethodBundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models
Wen, B., & Bekris, K. E. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9635991 · Cited by 187
“Furthermore, 3D model databases often require nontrivial manual effort and expert domain knowledge to build, involving steps such as scanning [20], mesh refinement [21] or CAD design.”
Lepard: Learning partial point cloud matching in rigid and deformable scenes
Li, Y., & Harada, T. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00547 · Cited by 186
“[28, 47], while the latter focuses on scenes that are non-rigidly deforming, e.”
BackgroundLearning to Infer Implicit Surfaces without 3D SupervisionPreprint
Liu, S., Saito, S., Chen, W., & Li, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.00767 · Cited by 186
“However, 3D model databases are still limited compared to the massive availability of 2D photos, especially since acquiring clean and high-fidelity ground-truth 3D models still requires a tedious 3D capture process [24, 25].”
BackgroundGrasping in the Wild: Learning 6DoF Closed-Loop Grasping From Low-Cost Demonstrations
Song, S., Zeng, A., Lee, J., & Funkhouser, T. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3004787 · Cited by 185
“The sign of that value indicates whether the voxel is in free space or occluded space [4, 22, 35].”
BackgroundLeveraging Shape Completion for 3D Siamese Tracking
Giancola, S., Zarzar, J., & Ghanem, B. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00145 · Cited by 184
“They are commonly used for 3D reconstruction [41, 18] but suffer from large-scale memory in-efficiency and require a space discretization which loses fine-grained details.”
BackgroundSonata: Self-Supervised Learning of Reliable Point Representations
Wu, X., DeTone, D., Frost, D., Shen, T., Xie, C., Yang, N., Engel, J. J., Newcombe, R. A., Zhao, H., & Straub, J. (2025) · 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/cvpr52734.2025.02067 · Cited by 190
Self-citationTopomap: Topological Mapping and Navigation Based on Visual SLAM Maps
Blöchliger, F., Fehr, M., Dymczyk, M., Schneider, T., & Siegwart, R. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460641 · Cited by 184
Understanding tools: Task-oriented object modeling, learning and recognition
Zhu, Y., Zhao, Y., & Zhu, S.-C. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298903 · Cited by 144
“We apply the KinectFusion algorithm [27] to generate a 3D reconstruction of the static scene, including a tool and an object.”
MethodPlan3D: Viewpoint and Trajectory Optimization for Aerial Multi-View Stereo Reconstruction
Hepp, B., Nießner, M., & Hilliges, O. (2018) · ACM Transactions on Graphics · doi:10.1145/3233794 · Cited by 181
“…volumetric fusion work by Curless and Levoy [Curless and Levoy 1996] whose implicit surface representation is at the core of most prominent real-time RGB-D reconstruction methods, such as Kinect Fusion [Newcombe et al. 2011] and many others [Chen et al. 2013; Dai et al. 2016; Nießner et al. 2013].”
MethodSelf-citationVisual and Visual‐Inertial SLAM: State of the Art, Classification, and Experimental Benchmarking
Servières, M., Renaudin, V., Dupuis, A., & Antigny, N. (2021) · Journal of Sensors · doi:10.1155/2021/2054828 · Cited by 181
“The last one is an extension of the KinectFusion algorithm for larger-scale environments.”
MethodRTG-SLAM: Real-time 3D Reconstruction at Scale using Gaussian Splatting
Peng, Z., Shao, T., Liu, Y., Zhou, J., Yang, Y., Wang, J., & Zhou, K. (2024) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3641519.3657455 · Cited by 182
Volumetric 3D mapping in real-time on a CPU
Steinbrücker, F., Sturm, J., & Cremers, D. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907127 · Cited by 178
“As most computations can be parallelized and executed by a GPU, Newcombe et al. [14] demonstrated with KinectFusion that camera tracking and geometry fusion is possible in real-time.”
BackgroundPGSR: Planar-Based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction
Chen, D., Li, H., Ye, W., Wang, Y., Xie, W., Zhai, S., Wang, N., Liu, H., Bao, H., & Zhang, G. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3494046 · Cited by 177
“We begin by rendering the depth for each training view, followed by utilizing the TSDF Fusion algorithm [65] to generate the corresponding TSDF field.”
Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation
Peng, R., Wang, R., Wang, Z., Lai, Y., & Wang, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00845 · Cited by 177
“Moreover, as the intermediate representation, the estimated depth maps of all individual images can be merged into a consistent point cloud [22] or a volumetric reconstruction [23], and the mesh can even be further reconstructed.”
BackgroundOctNetFusion: Learning Depth Fusion from Data
Riegler, G., Ulusoy, A. O., Bischof, H., & Geiger, A. (2017) · 2017 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00017 · Cited by 177
KillingFusion: Non-rigid 3D Reconstruction without Correspondences
Slavcheva, M., Baust, M., Cremers, D., & Ilic, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.581 · Cited by 177
“While many excellent solutions for the reconstruction of static scenes exist [5, 12, 23, 31, 33, 34, 43, 54], the more common real-life scenario - where objects move and interact non-rigidly - is still posing a challenge.”
BackgroundLearning Joint 2D-3D Representations for Depth Completion
Chen, Y., Yang, B., Liang, M., & Urtasun, R. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01012 · Cited by 177
“Truncated Signed Distance Function [24]) from the sparse depth image of the scene and applies 3D CNN to learn 3D representations and complete the scene densely in 3D.”
BackgroundObject discovery in 3D scenes via shape analysis
Karpathy, A., Miller, S., & Fei-Fei, L. (2013) · 2013 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2013.6630857 · Cited by 177
“We use the open source implementation of Kinect Fusion in the Point Cloud Library [3] to process the videos into 3D colored meshes with outward-facing normals.”
MethodInfluential3D Face Morphable Models "In-the-Wild"
Booth, J. G., Antonakos, E., Ploumpis, S., Trigeorgis, G., Panagakis, Y., & Zafeiriou, S. P. (2017) · 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.2017.580 · Cited by 177
SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
Dai, A., Diller, C., & Nießner, 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/cvpr42600.2020.00093 · Cited by 177
Editable free-viewpoint video using a layered neural representation
Zhang, J., Liu, X., Ye, X., Zhao, F., Zhang, Y., Wu, M., Zhang, Y., Xu, L., & Yu, J. (2021) · ACM Transactions on Graphics · doi:10.1145/3450626.3459756 · Cited by 177
CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation
Gadre, S. Y., Wortsman, M., Ilharco, G., Schmidt, L., & Song, S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02219 · Cited by 176
Dense 3D Object Reconstruction from a Single Depth View
Yang, B., Rosa, S., Markham, A., Trigoni, N., & Wen, H. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2868195 · Cited by 177
“Classic approaches usually fuse multiple depth images through iterative closest point (ICP) algorithms [4], [53], [54], while recent work [14] learns the 3D shape using deep neural nets from multiple depth views.”
BackgroundSalas-Moreno, R. F., Glocken, B., Kelly, P. H. J., & Davison, A. J. (2014) · 2014 IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2014.6948422 · Cited by 175
Self-citationIntroducing SLAMBench, a performance and accuracy benchmarking methodology for SLAM
Nardi, L., Bodin, B., Zia, M. Z., Mawer, J., Nisbet, A., Kelly, P. H. J., Davison, A. J., Lujan, M., O'Boyle, M. F. P., Riley, G., et al. (2015) · 2015 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2015.7140009 · Cited by 113
“These kernels are part of an initialisation step that is performed only at start-up. generateGaussian generates a Gaussian bell curve and stores it in a 1D array; initVolume initialises the 3D volume.”
BackgroundMethodSelf-citationFloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans
Liu, C., Wu, J., & Furukawa, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01231-1_13 · Cited by 175
Roth, H., & Vona, M. (2012) · Procedings of the British Machine Vision Conference 2012 · doi:10.5244/c.26.112 · Cited by 172
“KinectFusion [11] [13] integrates depth maps from the Kinect into a truncated signed distance formula (TSDF) representation [3].”
BackgroundMethodSelf-Supervised Visual Descriptor Learning for Dense Correspondence
Schmidt, T., Newcombe, R., & Fox, D. (2017) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2016.2634089 · Cited by 148
“KinectFusion ([17]), for rigid scenes, or DynamicFusion ([18]), for non-rigidly deforming scenes.”
BackgroundSelf-citationSimultaneous Localization and Mapping
Stachniss, C., Leonard, J. J., & Thrun, S. (2016) · Springer handbooks · doi:10.1007/978-3-319-32552-1_46 · Cited by 172
Practical SVBRDF acquisition of 3D objects with unstructured flash photography
Nam, G., Lee, J. H., Gutiérrez, D., & Kim, M. H. (2018) · ACM Transactions on Graphics · doi:10.1145/3272127.3275017 · Cited by 171
Sphere-meshes for real-time hand modeling and tracking
Tkach, A., Pauly, M., & Tagliasacchi, A. (2016) · ACM Transactions on Graphics · doi:10.1145/2980179.2980226 · Cited by 169
“For all these reasons, and as demonstrated by compelling results in rigid [Newcombe et al. 2011] and non-rigid [Newcombe et al.”
BackgroundTwo-View 3D Reconstruction for Food Volume Estimation
Dehais, J., Anthimopoulos, M., Shevchik, S., & Mougiakakou, S. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2642792 · Cited by 148
Real-time depth enhanced monocular odometry
Zhang, J., Kaess, M., & Singh, S. (2014) · 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2014.6943269 · Cited by 145
“As a convention in this paper, we use right superscript k, k ∈ Z+ to indicate image frames.”
MethodScalable inside-out image-based rendering
Hedman, P., Ritschel, T., Drettakis, G., & Brostow, G. (2016) · ACM Transactions on Graphics · doi:10.1145/2980179.2982420 · Cited by 153
“Unlike traditional methods for RGB-D reconstruction [Newcombe et al. 2011; Dai et al. 2016] and texturing [Zhou and Koltun 2014; Waechter et al. 2014], we aim to reproduce view-dependent appearance such as highlights, and to render accurate images even in regions where a global 3D reconstruction of…”
BackgroundMethodInfluentialDuLa-Net: A Dual-Projection Network for Estimating Room Layouts From a Single RGB Panorama
Yang, S.-T., Wang, F.-E., Peng, C., Wonka, P., Sun, M., & Chu, H. (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.2019.00348 · Cited by 168
“Closely related problems include depth estimation from a given image [32, 21] and scene reconstructions from point clouds [19, 18, 16].”
BackgroundSemantics for Robotic Mapping, Perception and Interaction: A Survey
Garg, S., Sünderhauf, N., Dayoub, F., Morrison, D., Cosgun, A., Carneiro, G., Wu, Q., Chin, T.-J., Reid, I., Gould, S., et al. (2020) · Foundations and Trends® in Robotics · doi:10.1561/2300000059 · Cited by 105
MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds
Tang, Z., Fan, Y., Wang, D., Xu, H., Ranjan, R., Schwing, A. G., & Yan, Z. (2025) · 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/cvpr52734.2025.00498 · Cited by 168
“…reconstructs a scene using either explicit representations ( e.g ., 3D point, mesh) or implicit representations ( e.g ., signed distance function [43]), recent approaches adopt different neural representations [55], including Neural Distance Fields [16, 38], Neural Radi-ance Fields (NeRFs) [3,…”
User-Defined Gestures for Augmented Reality
Piumsomboon, T., Clark, A., Billinghurst, M., & Cockburn, A. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40480-1_18 · Cited by 167
BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
Wen, B., Tremblay, J., Blukis, V., Tyree, S., Müller, T., Evans, A., Fox, D., Kautz, J., & Birchfield, S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00066 · Cited by 166
“For DROID-SLAM [61], NICE-SLAM [85] and KinectFusion [43], when working in an object-centric setting, significantly less texture or geometric (purely planar or cylindrical object surfaces) cues can be leveraged for tracking, leading to poor performance.”
BackgroundMethodInfluentialComputer Vision Metrics: Survey, Taxonomy, and Analysis
Krig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5 · Cited by 166
Zhang, J., Yang, X., Wang, W., Guan, J., Ding, L., & Lee, V. C. S. (2023) · Automation in Construction · doi:10.1016/j.autcon.2022.104699 · Cited by 165
Motion2fusion: real-time volumetric performance capture
Dou, M., Davidson, P., Fanello, S. R., Khamis, S., Kowdle, A., Rhemann, C., Tankovich, V., & Izadi, S. (2017) · ACM Transactions on Graphics · doi:10.1145/3130800.3130801 · Cited by 165
“We use a TSDF volume as the underlying data structure for fusion [Curless and Levoy 1996; Newcombe et al. 2011].”
MethodSelf-citationNeural RGB®D Sensing: Depth and Uncertainty From a Video Camera
Liu, C., Gu, J., Kim, K., Narasimhan, S. G., & Kautz, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01124 · Cited by 142
“Its output can be directly fed into classical RGB-D based 3D scanning methods [31, 32] for 3D reconstruction.”
BackgroundMethodInfluentialHa, S., Yeon, J., & Yu, H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72764-1_11 · Cited by 165
Fast visual odometry and mapping from RGB-D data
Dryanovski, I., Valenti, R. G., & Xiao, J. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630889 · Cited by 164
“Recently, Newcombe et al. [7] presented a system for RGB-D pose tracking and mapping.”
BackgroundKlingensmith, M., Dryanovski, I., Srinivasa, S., & Xiao, J. (2015) · Robotics: Science and Systems XI · doi:10.15607/rss.2015.xi.040 · Cited by 163
Schunck, D., Magistri, F., Rosu, R. A., Cornelißen, A., Chebrolu, N., Paulus, S., Léon, J., Behnke, S., Stachniss, C., Kuhlmann, H., et al. (2021) · PLOS ONE · doi:10.1371/journal.pone.0256340 · Cited by 163
“Several algorithms such as Poisson [45], TSDF [46, 47] etc.”
MethodInverse Path Tracing for Joint Material and Lighting Estimation
Azinović, D., Li, T., Kaplanyan, A., & Nießner, M. (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.2019.00255 · Cited by 163
“With the availability of inexpensive, commodity RGB-D sensors, such as the Microsoft Kinect, Google Tango, or Intel RealSense, we have seen incredible advances in 3D reconstruction techniques [27, 14, 28, 33, 8].”
MethodFoundPose: Unseen Object Pose Estimation with Foundation Features
Örnek, E. P., Labbé, Y., Tekin, B., Ma, L., Keskin, C., Förster, C., & Hodaň, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73347-5_10 · Cited by 163
Li, H., Vouga, E., Gudym, A., Luo, L., Barron, J. T., & Gusev, G. (2013) · ACM Transactions on Graphics · doi:10.1145/2508363.2508407 · Cited by 162
“Real-time 3D reconstruction methods from continuous streams of depth maps [Rusinkiewicz et al. 2002; Newcombe et al. 2011] are all based on ICP since consecutive scans are temporally coherent.”
MethodSigned Distance Fields: A Natural Representation for Both Mapping and Planning
Oleynikova, H., Millane, A., Taylor, Z., Galceran, E., Nieto, J. I., & Siegwart, R. (2016) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-a-010820134 · Cited by 162
“Heng Weighing [24], (e) TSDF (truncation radius not shown) [2], and (f) the TSDF weights along this ray [12].”
BackgroundMethodInfluentialEfficient Learning on Point Clouds With Basis Point Sets
Prokudin, S., Lassner, C., & Romero, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00443 · Cited by 162
“Truncated signed distance fields (TSDFs) [8, 31, 38, 42, 48, 9, 33] can be viewed as a natural extension of occupancy grids: they store distance-to-surface information in grid cells instead of a simple occupancy flag.”
BackgroundRaDe-GS: Rasterizing Depth in Gaussian Splatting
Zhang, B., Fang, C., Shrestha, R., Liang, Y., Long, X., & Tan, P. (2026) · ACM Transactions on Graphics · doi:10.1145/3789201 · Cited by 163
“Stereo and multi-view stereo methods recover a depth map for each input image, which can be fused into a complete 3D model with truncated signed distance functions (TSDF) [Curless and Levoy 1996a; Newcombe et al. 2011; Zach et al. 2011].”
InfluentialTAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement
Doersch, C., Yang, Y., Vecerik, M., Gokay, D., Gupta, A., Aytar, Y., Carreira, J., & Zisserman, A. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00923 · Cited by 161
“This approach has been used across many high-precision estimation problems in computer vision [7, 26, 30, 36, 39, 53, 64, 68, 73].”
MethodAugmented Reality Platforms for Virtual Fitting Rooms
Pachoulakis, I. (2012) · The International journal of Multimedia & Its Applications · doi:10.5121/ijma.2012.4404 · Cited by 120
“The Kinect algorithm discussed in [25] uses a low-cost depth camera and commodity graphics hardware to create accurate real-time depth mappings of complex and arbitrary indoor scenes in variable lighting conditions.”
MethodMap-Free Visual Relocalization: Metric Pose Relative to a Single Image
Arnold, E. H., Wynn, J., Vicente, S., Garcia-Hernando, G., Monszpart, Á., Prisacariu, V. A., Turmukhambetov, D., & Brachmann, E. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19769-7_40 · Cited by 163
Pan, Y., Zhong, X., Wiesmann, L., Posewsky, T., Behley, J., & Stachniss, C. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3422055 · Cited by 160
“Various approaches have been proposed to improve the scalability and efficiency of the map data structure [19], [49], [77] and to realize the incremental integration from sensor measurements [50] for the dense volumetric mapping.”
MethodReal-Time Camera Tracking: When is High Frame-Rate Best?
Handa, A., Newcombe, R. A., Angeli, A., & Davison, A. J. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33786-4_17 · Cited by 159
“…now is so good that we strongly believe that it will soon be standard to assume that dense surface scene models are available as a matter of course in vision problems involving moving cameras (especially with the option of augmenting monocular video with commodity depth camera sensing, e.g. [7]).”
BackgroundSelf-citationEvent-based 3D SLAM with a depth-augmented dynamic vision sensor
Weikersdorfer, D., Adrian, D. B., Cremers, D., & Conradt, J. (2014) · 2014 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2014.6906882 · Cited by 137
“An important example for a 3D SLAM algorithm is KinectFusion [5], a dense 3D SLAM algorithm which uses iterative closest point to match depth images and a signed distance volume as a 3D map.”
BackgroundMethodReal-Time Posture Reconstruction for Microsoft Kinect
Shum, H. P. H., Ho, E. S. L., Jiang, Y., & Takagi, S. (2013) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2013.2275945 · Cited by 159
The History of Mobile Augmented RealityPreprint
Arth, C., Grasset, R., Gruber, L., Langlotz, T., Mulloni, A., & Wägner, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.01319 · Cited by 159
“Later at ISMAR 2011, Richard Newcombe presents the KinectFusion work [47], in which depth images from the Kinect sensor are fused to create a single implicit surface model.”
MethodSceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
Wu, S.-C., Wald, J., Tateno, K., Navab, N., & Tombari, F. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00743 · Cited by 158
“Boosted by the availability of inexpensive depth sensors, real-time dense SLAM algorithms [35, 22, 37, 59] and large scale 3D datasets [5, 56], the research focus has shifted from reconstructing the 3D scene geometry to enhancing the 3D maps with semantic information about scene components.”
BackgroundNeural 3D Scene Reconstruction with the Manhattan-world Assumption
Guo, H., Peng, S., Lin, H., Wang, Q., Zhang, G., Bao, H., & Zhou, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00543 · Cited by 158
A Review on Viewpoints and Path Planning for UAV-Based 3-D Reconstruction
Maboudi, M., Homaei, M., Song, S., Malihi, S., Saadatseresht, M., & Gerke, M. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3276427 · Cited by 158
“They incrementally updated the TSDF model by scanning from an NBV until no ISE was detected.”
BackgroundMethodInfluentialLarge-Scale Multi-resolution Surface Reconstruction from RGB-D Sequences
Steinbrucker, F., Kerl, C., & Cremers, D. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.405 · Cited by 158
“It is important to note that approaches that track the camera pose with respect to the reconstructed model (such as all existing KinectFusion-based methods [12] [21] [20]) are inherently prone to drift.”
BackgroundMethodInfluentialLocalization as a Key Enabler of 6G Wireless Systems: A Comprehensive Survey and an Outlook
Trevlakis, S. E., Boulogeorgos, A. A., Pliatsios, D., Querol, J., Ntontin, K., Sarigiannidis, P. G., Chatzinotas, S., & Renzo, M. D. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3324952 · Cited by 159
Exploiting uncertainty in regression forests for accurate camera relocalization
Valentin, J., Niebner, M., Shotton, J., Fitzgibbon, A., Izadi, S., & Torr, P. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299069 · Cited by 156
“Simultaneous Localization and Mapping (SLAM) systems such as [14] [15] [17] [7] and commercial systems such as HoloLens or Project Tango demonstrate that visual SLAM is a maturing technology.”
BackgroundSelf-citationIndoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey
Naseer, M., Khan, S. S., & Porikli, F. (2018) · IEEE Access · doi:10.1109/access.2018.2886133 · Cited by 156
“densely overlapping RGB-D views of an object [159], [160] is relatively a simpler problem, here we focus on scene reconstruction from either a single or a set of RGB-D images with partial occlusions leading to incomplete information.”
BackgroundCloud-Based Collaborative 3D Mapping in Real-Time With Low-Cost Robots
Mohanarajah, G., Usenko, V., Singh, M., D’Andrea, R., & Waibel, M. (2015) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2015.2408456 · Cited by 155
“It is clearly visible that bandwidth is proportional to the velocity of the robot, with the highest bandwidth about For purposes of comparison, note that our cloud-based KinectFusion [29], a dense mapping algorithm, uses around 3.5 MB/s since all frames must be sent to the cloud for processing.”
BackgroundInfluentialProcedurally generated virtual reality from 3D reconstructed physical space
Sra, M., Garrido-Jurado, S., Schmandt, C., & Maes, P. (2016) · ACM Symposium on Virtual Reality Software and Technology (VRST) · doi:10.1145/2993369.2993372 · Cited by 155
SuPer: A Surgical Perception Framework for Endoscopic Tissue Manipulation With Surgical Robotics
Li, Y., Richter, F., Lu, J., Funk, E. K., Orosco, R. K., Zhu, J., & Yip, M. C. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2970659 · Cited by 155
“72) at pixel coordinate (u, v) where nz is the z component of camera frame normal, f is the cameras focal length, and dc is the normalized distance from the pixel coordinate to the center of the image [10][11].”
BackgroundMethodInfluentialDifferentiable signed distance function rendering
Vicini, D., Speierer, S., & Jakob, W. (2022) · ACM Transactions on Graphics · doi:10.1145/3528223.3530139 · Cited by 156
Splat-SLAM: Globally Optimized RGB-Only SLAM with 3D Gaussians
Sandström, E., Zhang, G., Tateno, K., Oechsle, M., Niemeyer, M., Zhang, Y., Patel, M., Gool, L. V., Oswald, M. R., & Tombari, F. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00156 · Cited by 158
“…map by optimizing a neural implicit encoding of the scene, either as weights of an MLP [1, 39, 45, 57], as features anchored in dense grids [3, 29, 42, 51, 58, 66, 67, 79, 81], using hierarchical octrees [71], via voxel hashing [8, 40, 49, 76, 77], point clouds [18, 30, 50] or axis-aligned…”
3D scanning deformable objects with a single RGBD sensor
Dou, M., Taylor, J., Fuchs, H., Fitzgibbon, A. W., & 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.2015.7298647 · Cited by 154
“However, many existing 3D scanning systems (e.g. [14, 9]) use rigid alignment algorithms and thus require the object or scene being scanned to remain static.”
BackgroundSelf-citationSimpleRecon: 3D Reconstruction Without 3D Convolutions
Sayed, M., Gibson, J., Watson, J., Prisacariu, V. A., Firman, M., & Godard, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19827-4_1 · Cited by 154
Real-time monocular object SLAM
Gálvez‐López, D., Salas, M., Tardós, J. D., & Montiel, J. M. M. (2015) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2015.08.009 · Cited by 153
Layer Depth Denoising and Completion for Structured-Light RGB-D Cameras
Shen, J., & Cheung, S.-C. S. (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.2013.157 · Cited by 153
“Generic image denoising and complete algorithms fail to take into account the unique problems of structured-light RGB-D systems.”
Background
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.