DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time
The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Abstract
We present the first dense SLAM system capable of reconstructing non-rigidly deforming scenes in real-time, by fusing together RGBD scans captured from commodity sensors. Our DynamicFusion approach reconstructs scene geometry whilst simultaneously estimating a dense volumetric 6D motion field that warps the estimated geometry into a live frame. Like KinectFusion, our system produces increasingly denoised, detailed, and complete reconstructions as more measurements are fused, and displays the updated model in real time. Because we do not require a template or other prior scene model, the approach is applicable to a wide range of moving objects and scenes.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In the SLAM community, Newcombe et al. [182] have address the non-rigid case for small-scale reconstruction.”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [182]
Citations
Cites
KinectFusion: Real-time dense surface mapping and tracking
Newcombe, R. A., Fitzgibbon, A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A. J., Kohi, P., Shotton, J., & Hodges, S. (2011) · 2011 10th IEEE International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2011.6092378 · Cited by 4,008 · cited 14×
“As in KinectFusion, volumetric TSDF memory limits geometric extent; but there are many solutions to this in the literature.”
MethodInfluentialSelf-citationA 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 3×
“The truncation distance τ > 0 and the updated TSDF value is given by the weighted averaging scheme [5], with the weight truncation introduced in [18]:”
BackgroundMethodKinectFusion: 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 13×
“As in KinectFusion, volumetric TSDF memory limits geometric extent; but there are many solutions to this in the literature.”
MethodInfluentialSelf-citationReal-time 3D reconstruction at scale using voxel hashing
Nießner, M., Zollhöfer, M., Izadi, S., & Stamminger, M. (2013) · ACM Transactions on Graphics · doi:10.1145/2508363.2508374 · Cited by 1,002 · cited 1×
“KinectFusion spurred a flurry of follow up research aimed at robustifying the tracking [9, 32] and expanding its spatial mapping capabilities to larger environments [22, 19, 34, 31, 9].”
BackgroundEfficient model-based 3D tracking of hand articulations using Kinect
Oikonomidis, I., Kyriazis, N., & Argyros, A. (2011) · Procedings of the British Machine Vision Conference 2011 · doi:10.5244/c.25.101 · Cited by 874 · cited 1×
“The best of these demonstrate high accuracy, real-time performance capture for tracking faces [16, 3], hands [21, 20], complete bodies [27], or general articulated objects [23, 33].”
BackgroundKintinuous: Spatially Extended KinectFusion
Whelan, T. J., Kaess, M., Fallon, M. F., Johannsson, H., Leonard, J. J., & McDonald, J. (2012) · Maynooth University ePrints and eTheses Archive (Maynooth University) · Cited by 624
Realtime and Robust Hand Tracking from Depth
Qian, C., Sun, X., Wei, Y., Tang, X., & Sun, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.145 · Cited by 470
Embedded deformation for shape manipulation
Sumner, R. W., Schmid, J., & Pauly, M. (2007) · ACM SIGGRAPH 2007 papers · doi:10.1145/1275808.1276478 · Cited by 449 · cited 3×
“Hierarchical Deformation Tree: In original applications of the embedded deformation graph [25] approach to non-rigid tracking, E is defined as the k−nearest neighbours of each node or all nodes within a specified radius.”
BackgroundInfluentialReal-time non-rigid reconstruction using an RGB-D camera
Zollhöfer, M., Nießner, M., Izadi, S., Rehmann, C., Zach, C., Fisher, M., Wu, C., Fitzgibbon, A., Loop, C., Theobalt, C., et al. (2014) · ACM Transactions on Graphics · doi:10.1145/2601097.2601165 · Cited by 405 · cited 1×
“Recently, [37] demonstrated an impressive real-time version of a similar technique, using GPU accelerated optimisations.”
MethodGlobal Correspondence Optimization for Non‐Rigid Registration of Depth Scans
Li, H., Sumner, R. W., & Pauly, M. (2008) · Computer Graphics Forum · doi:10.1111/j.1467-8659.2008.01282.x · Cited by 399 · cited 1×
“Practical advancements to pairwise 3D shape and scan alignment over larger deformations make use of reduced deformable model parametrisations [14, 4].”
Method
Research works printed but not linked: 1
- curless, 1997, New Methodsfor Surface Reconstructionfrom Range Images
Cited by
Items 801–900 of 956
LiVo: Toward Bandwidth-adaptive Fully-Immersive Volumetric Video Conferencing
Ghosh, R., Shin, C. S., Zhang, L., Ye, M., Jin, T., Madhyastha, H. V., Netravali, R., Ortega, A., Rao, S., Rowe, A., et al. (2025) · Proceedings of the ACM on Networking · doi:10.1145/3768981 · Cited by 1
Multi-view dynamic reconstruction with cross-view smoothing based on surfel
Han, S., Liu, X., Dong, Z., Luo, J., Ma, X., & Kuang, H. (2025) · Machine Vision and Applications · doi:10.1007/s00138-025-01777-7 · Cited by 1
SNH-SLAM: Implicit Dense SLAM Based on Scalable Neural-Hash Representation
Li, X., Wen, Z., Dong, Z., Duan, H., Chen, T., & Hong, Z. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3651044 · Cited by 1
“Subsequently, researchers made various improvements to KinectFusion, including optimizing memory usage [17], [18], implementing loop closure [19], adapting to dynamic environments [20], [21], and enhancing tracking performance [22].”
PortaCap: Portable Volumetric Video Capturing System for Metaverse Interaction
Zhang, C., Huang, Y., Zhu, Y., Qiao, L., Cai, D., Fang, S., Wang, C., Zhang, H., & Qi, M. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3655072 · Cited by 1
“(cid:2) Real-time Volumetric Content Generation: Generating high-quality, free-viewpoint volumetric content requires comprehensive multi-angle fusion [23], [24], [25], [26].”
Motion2VecSets: Non-Rigid Shape Reconstruction and Tracking With 4D Latent Set Diffusion
Tang, J., Cao, W., Zhang, B., Luo, C., Liu, Y., & Nießner, M. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3680779 · Cited by 4
“For non-rigid object reconstruction and tracking, approaches like DynamicFusion [5], VolumeDeform [6], and DoubleFusion [7] jointly perform surface fusion and motion tracking by leveraging handcrafted deformation priors, such as As-Rigid-As-Possible (ARAP) [8] and Embedded Deformation [9].”
Tessellation GS: Neural Mesh Gaussians for Robust Monocular Reconstruction of Dynamic Objects
Tao, S., Zhou, B., Tu, H., Wang, Y., & Liu, Y. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00103 · Cited by 1
“Early approaches [4, 31] employed image warping to preserve observed information for novel view synthesis or physical plausibility regularization in unobserved regions for geometry reconstruction.”
Duan, H., Hu, S., Wang, F., Shimasaki, K., & Ishii, I. (2026) · Sensors · doi:10.3390/s26113457 · Cited by 1
“For non-rigid scenes, temporal fusion methods such as DynamicFusion [30] and Fusion4D [31] accumulate depth information across frames using deformable tracking, and de Aguiar et al. [32] https://doi.org/10.3390/s26113457 demonstrated that sparse multi-view video, combined with temporal coherence…”
InfluentialCombining color and depth for precise and detailed 3D geometry of clothed human
Luo, J., & Guo, Y. (2026) · Computers & Graphics · doi:10.1016/j.cag.2026.104674 · Cited by 1
Language-4D Cross-Boosting for Generalized Zero-Shot 6DoF Tracking and 3D Reconstruction
Sun, J., Wang, Y., Zhao, J., Zhang, Y., Liu, M., & Shou, M. Z. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3711593 · Cited by 1
“Many efforts have focused on free-form tracking without any geometric prior, such as DynamicFusion [52] and Deepdeform [53].”
Deep object tracking with multi-modal data
Zhang, X., Yuan, Y., & Lu, X. (2016) · International Conference on Computer, Information and Telecommunication Systems · doi:10.1109/cits.2016.7546403 · Cited by 1
“Recently, a few multi-modal visual tracking methods have been developed [4], [5].”
BackgroundA real-time 3D end-to-end augmented reality system (and its representation transformations)
Tytgat, D., Aerts, M., Busser, J. D., Lievens, S., Alface, P. R., & Macq, J. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2237804 · Cited by 1
CT from Motion: Volumetric Capture of Moving Shapes with X-rays and Videos
Pansiot, J., & Boyer, E. (2017) · HAL · Cited by 1
Self-supervised online learning of appearance for 3D tracking
Lee, B., & Lee, D. D. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206373 · Cited by 1
“There also have been model-free 3D/RGBD tracking solutions developed in different contexts, [19], [20], [21], [22], [23] for instance.”
BackgroundElastic Alignment of Triangular Surface Meshes
Sánta, Z., & Kató, Z. (2018) · International Journal of Computer Vision · doi:10.1007/s11263-018-1084-4 · Cited by 1
Real-time Human Body Correspondences for Motion Tracking
He, C., & Xiao, S. (2018) · International Conference on Image and Graphics Processing (ICIGP) · doi:10.1145/3191442.3191444 · Cited by 1
“Current methods approach non-rigid surface tracking as an optimization problem, by defining an energy function of corresponding points between template model and frame data, and iteratively updating the function until it reaches a minimum[6][7][8][9].”
MethodSegmentedFusion: 3D Human Body Reconstruction Using Stitched Bounding Boxes
Yao, S. H., Thomas, D., Sugimoto, A., Lai, S., & Kyushu, R.-I. T. (2018) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2018.00031 · Cited by 1
“Another approach to reconstruction is based on templatefree techniques [8, 10, 15, 19].”
BackgroundMethodInfluentialA Comparison of Scene Flow Estimation Paradigms
Tsekourakis, I., & Mordohai, P. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-19816-9_1 · Cited by 1
“Moreover, monocular inputs hinder free-viewpoint video applications since texture information is not available for even the slightest viewpoint changes, with a few exceptions [12, 13].”
BackgroundMethodReducing the cost of visual DL datasets
Osteen, P. R., Owens, J. L., & Kaukeinen, B. (2019) · Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications · doi:10.1117/12.2519114 · Cited by 1
Robot Localisation in 3D Environments Using Sparse Range Measurements
Arukgoda, J., Ranasinghe, R., & Dissanayake, G. (2019) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2019.8868466 · Cited by 1
“Even though SDF avoids this issue, and a truncated version is widely used for matching point clouds [12][13], a clear definition of “inside” and “outside”, which is difficult to define apriori in complex environments is required.”
BackgroundZhuravlev, A. V., Dong, G., Razevig, V. V., Chizh, M. A., & Boxiong, H. (2019) · Photonics & Electromagnetics Research Symposium - Fall (PIERS-Fall) · doi:10.1109/piers-fall48861.2019.9021840 · Cited by 1
“In the future, it will be necessary to adapt one of such methods, for example, DensePose [12], DynamicFusion [13], VolumeDeform [14], SurfelWarp [15], etc.”
MethodReconstructing 3D Human Avatars from Monocular Images
Alldieck, T., Kappel, M., Castillo, S., & Magnor, M. A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-41816-8_8 · Cited by 1
“in [163] generalized KinectFusion to non-rigid objects.”
BackgroundMethodInfluentialChen, C.-F., & Rosenberg, E. S. (2020) · ACM Symposium on Virtual Reality Software and Technology (VRST) · doi:10.1145/3385956.3418952 · Cited by 1
“, [20, 26]), to-our-best-knowledge, texture/reflectance reconstruction for dynamically moving objects”
BackgroundCompression and Completion of Animated Point Clouds using Topological Properties of the Manifold
Pan, L., Ladický, Ľ., & Pollefeys, M. (2020) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv50981.2020.00083 · Cited by 1
“This motivated a research on non-rigid reconstruction by iterative warping of estimated geometry into the live frame [24].”
A Review on Real-Time 3D Reconstruction Methods in Dynamic Scene
Nor’a, M. N. A., Fadzli, F. E., & Ismail, A. W. (2021) · International Journal of Innovative Computing · doi:10.11113/ijic.v12n1.317 · Cited by 1
“The connection update step and the cooperative deformation step, which compensate the deformation of the skeleton as well as the graph-node, are the major discrepancies from the DynamicFusion [19] pipeline.”
BackgroundVision-Based 3D Reconstruction Using a Compound Eye Camera
Oh, W., Yoo, H., Ha, T., & Oh, S. (2021) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas52745.2021.9649968 · Cited by 1
Novel View Synthesis of Dynamic Human with Sparse Cameras
Lv, X., Wang, Y., Xu, F., Nie, J., Xu, F., & Gao, H. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-93046-2_37 · Cited by 1
3DCADFusion: Tracking and 3D Reconstruction of Dynamic Objects without External Motion Information
Salari, A., Nozdryn-Plotnicki, A., Afrooze, S., & Najjaran, H. (2021) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc52423.2021.9658735 · Cited by 1
“DynamicFusion [9] aligns deforming scenes by warping non-rigid geometries using volumetric motion fields.”
MethodVision-Based Body Activity Recognition
Hu, Z., & Lv, C. (2022) · SpringerBriefs in intelligent systems · doi:10.1007/978-981-19-2290-9_4 · Cited by 1
Study of Vocal Muscle Strain with Skin Deformation Tracking System
Hogue, S., Shembel, A. C., & Guo, X. (2022) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms55023.2022.00026 · Cited by 1
“Deriving from KinectFusion [24], then DynamicFusion [25], many methods have been developed to take RGBD video as input to recreate full body human avatars [11], [42], [43].”
MethodDifferentiable Deformation Graph-Based Neural Non-rigid Registration
Feng, W., Cai, H., Hou, J., Deng, B., & Zhang, J. (2023) · Communications in Mathematics and Statistics · doi:10.1007/s40304-023-00341-x · Cited by 1
“For example, it plays a key role in tracking [42, 55], reconstruction [39, 40], and many other tasks.”
BackgroundTemporally consistent reconstruction of 3D clothed human surface with warp field
Deng, Y., Li, B., Yang, Y., & Zhao, X. (2023) · Image and Vision Computing · doi:10.1016/j.imavis.2023.104782 · Cited by 2
Modeling Dynamic Clothing for Data-Driven Photorealistic Avatars
Xiang, D. (2023) · doi:10.1145/3623053.3623373 · Cited by 1
“An alternate approach for telepresence relies heavily on the availability of sensory inputs without a strong human prior, including those based on volumetric fusion methods [Newcombe et al. 2015], neural implicit functions [Yu et al. 2021], or neural radiance fields [Lin et al. 2022].”
BackgroundNeural Radiance Fields for Dynamic View Synthesis Using Local Temporal Priors
Chen, R., Zhao, J., Zhang, F., Chalmers, A., & Rhee, T. J. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2095-8_5 · Cited by 1
“Another solution is to reconstruct a canonical space representation of the scene, and use an associated warp field to model per-frame deformation in the scene [28].”
BackgroundHumanReg: Self-supervised Non-rigid Registration of Human Point Cloud
Chen, Y., Pan, Z., Zhong, Z., Guo, W., Feng, J., & Zhou, J. (2024) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv62453.2024.00067 · Cited by 3
“At scene level, DynamicFusion [52] finds correspondences by matching the depth map of adjacent frame based on a coarse warping field.”
BackgroundIndoor Autonomous Navigation with EdgeSLAM
Xu, J., Yang, Z., Liu, Y., & Cao, H. (2024) · Springer eBooks · doi:10.1007/978-981-97-3573-0_5 · Cited by 1
AI + AR-Assisted Manufacturing
Liu, T., Bao, J., Zheng, Y., & Lu, Y. (2025) · Springer series in advanced manufacturing · doi:10.1007/978-3-031-81477-8_12 · Cited by 1
Neural Fields for Multimedia Applications (Part-2): Trends in Volumetric Videos and 3D Objects
Muraleedharan, L. P., Liu, J., Dutta, U. K., Choudhury, A., & Su, G. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-82475-3_20 · Cited by 1
DynORecon: Dynamic Object Reconstruction for Navigation
Wang, Y., Morris, J., Wu, L., Vidal‐Calleja, T., & Ila, V. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128794 · Cited by 1
“Recent developments in both state-of-the-art dense reconstruction methods identify and address the complications of dynamic environments [10], [11], [12], [13], [14], [15], each of which focuses on one aspect of reconstruction to handle dynamics more efficiently.”
Real-Time Consistent Monocular Depth Recovery System for Dynamic Environments
Huang, G., Pan, X., Lin, H., Zhang, Z., Xu, W., & Zhang, G. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246257 · Cited by 1
“Other works [17], [18] leverage optical flow and post-processing for 4D reconstruction, where optical flow priors help differentiate between static and dynamic regions, followed by a global optimization step to refine depth predictions.”
Real-time Surface Deformation Recovery from Stereo Videos
Zhou, H., & Jayender, J. (2020) · PubMed · doi:10.48550/arxiv.2007.08576 · Cited by 1
“e parameters of the control points to make the deformed template match the output of the GPU-based stereo matching method. The algorithms are parallelized and run on the GPU. Similar to DynamicFusion [4], we employ dual-quaternion to represent deformation and each control point i is assigned a dual-quaternion Wt i to…”
MethodInteracting with Spatial Augmented RealityPreprint
Roo, J. S., & Hachet, M. (2016) · HAL · Cited by 1
Volumetric tracking of 3D deformable shapes
Allain, B. (2017) · theses.fr (ABES) · doi:10.70675/bc72ac94zbb56z4dd0z826cz138ab65aea2f · Cited by 1
“For differentiability and merging purposes, the occupancy function might be replaced by a smooth function, such as the truncated signed distance function (TSDF) [25] which has proven successful for fusing range sensor data [26, 27].”
BackgroundInfluentialExtended Kalman Filter SLAM Implementation for a Differential Robot with LiDAR
Qader, A., & Fayez, H. F. (2018) · Research Commons (University of Waikato) · Cited by 2
Skeleton Driven Non-rigid Motion Tracking and 3D ReconstructionPreprint
Elanattil, S., Moghadam, P., Denman, S., Sridharan, S., & Fookes, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.03774 · Cited by 1
“Thirdly, volumetric fusion is carried out as in state-of-the-art approaches [3], [1], [2].”
BackgroundMethodResultInfluentialThermal-Kinect Fusion Scanning System for Bodyshape Inpainting and Estimation under Clothing
Tisha, S. M. (2019) · Louisiana State University · doi:10.31390/gradschool_theses.5018 · Cited by 3
“In the model-free approaches the researchers estimate non-rigid 3D shape over time [38], [39], [40], [8].”
Unberath, M., Yu, K. K., Barmaki, R., Johnson, A. A., & Navab, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.02884 · Cited by 1
“In this case, more sophisticated tracking solutions are required that employ dense or sparse methods, such as deformable SLAM [24,40] or human skeleton tracking [56,57].”
MethodNRST: Non-rigid Surface Tracking from Monocular VideoPreprint
Habermann, M., Xu, W., Rhodin, H., Zollhöfer, M., Pons‐Moll, G., & Theobalt, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.02407 · Cited by 1
Visual tracking of deformable objects with RGB-D camera
Sengupta, A. (2020) · theses.fr (ABES) · doi:10.70675/9d7fb160z245fz4c09z924cz755d392ced2c · Cited by 1
A Perspective on Open Challenges in Deformable Object Manipulation
McKennaa, R. P., & Oyekan, J. (2026) · arXiv · doi:10.48550/arxiv.2602.22998 · Cited by 1
“Advances in computer vision have recently led to effective methods for reconstructing DOs in real-time, which dynamically adapt the tracking model to counteract occlusion issues [30], [31].”
Multi-Volume High Resolution RGB-D Mapping with Dynamic Volume PlacementPreprint
Salvato, M. A., Finman, R., & Leonard, J. J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.07106
“These limitations have spawned other algorithms such as [53], which uses octrees to map larger spaces to partial overcome the finite scope of KinectFusion, and [33] which allows for accurate reconstruction even for slowly moving objects.”
BackgroundRe-parameterization of a Deformation Model for Non-rigid Registration
Cao, V.-T., Tran, T.-T., & Laurendeau, D. (2016) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0005714300370047
“Instead of using affine transformations for points (nodes) of a sparsely sampled set, the methods in (Bonarrigo et al., 2014; Newcombe et al., 2015) specify only rigid transformations for these points and then use dual-quaternion blending for the interpolation step.”
BackgroundMethodEnhancing real-time full 3D reconstruction of humans with pre-scanned meshes
Vretos, N., Alexiadis, D. S., Zarpalas, D., & Daras, P. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532526
“The full 3D reconstruction aspects is also significantly researched [8]-[11].”
BackgroundBody Part Modeling on the Phone
MARIGGIS, I., Saurer, O., & Tanskanen, P. (2016) · International Conference on 3D Body Scanning Technologies (3DBST) · doi:10.15221/16.214
“The advantage of those sensor is that they provide high metric accuracy within a certain range [NIH + 11] and can capture large spaces quickly [NZIS13] and even dynamic scenes [NFS15, DKD + 16].”
Expression invariant 3D face modeling from an RGB-D video
Kim, D., Choi, J., Leksut, J. T., & Medioni, G. G. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7899989
“[8] present a SLAM system which extends KinectFusion.”
Background4D ISIP: 4D Implicit Surface Interest Point Detection
Li, S., Yılmaz, A., Xiao, C., & Li, H. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-71607-7_15
“Newcombe [15] proposed a real-time method to reconstruct dynamic scenes without any prior templates.”
BackgroundMethodInfluentialCreating Immersive Virtual Reality Scenes Using a Single RGB-D Camera
Lai, P. K., & Laganière, R. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59876-5_25
An Effective Approach for Point Clouds Registration Based on the Hard and Soft AssignmentsPreprint
Jin, C., Zhu, J., Li, Y., Du, S., Li, Z., & Lu, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.00227
Non-rigid Reconstruction of Casting Process with Temperature Feature
Lin, J., Wang, Y., Li, X. S., Wang, Y., & Wang, L. (2017) · 3D Research · doi:10.1007/s13319-017-0143-x
Temporal and Physical Reasoning for Perception-Based Robotic ManipulationPreprint
Jonathan, F., Paxton, C., & Hager, G. D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.03948
“This work was continued in DynamicFusion [7], which added support for moving and deformable objects.”
BackgroundNon-Iterative Localization and Fast Mapping.Preprint
Wang, C., Xie, L., & Yuan, J. (2017) · arXiv (Cornell University)
Color Mapping for 3D Geometric Models without Reference Image Locations
Li, F., Du, Y., Tian, H., & Liu, R. (2017) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2017.8227418
“years [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14], [15], [16].”
Frequency-Domain Joint Motion and Disparity Estimation Using Steerable Filters
Alexiadis, D. S., Mitianoudis, N., & Stathaki, T. (2018) · Inventions · doi:10.3390/inventions3010012
Application of 3D reconstruction system in diabetic foot ulcer injury assessment
Li, J., Jiang, L., Li, T., & Liang, X. (2018) · AIP conference proceedings · doi:10.1063/1.5033783
Automated Scene Understanding from Aerial Imagery
Guo, X. (2018) · Queensland University of Technology · doi:10.5204/thesis.eprints.117973
Affect-Preserving Visual Privacy Protection
Xu, W. (2018) · UKnowledge (University of Kentucky) · doi:10.13023/etd.2018.303
Towards force-correlated ultrasound volume elastography
Graule, M. A. (2017) · DSpace@MIT (Massachusetts Institute of Technology)
Surface motion capture animation
Boukhayma, A. (2017) · theses.fr (ABES) · doi:10.70675/e581b05az8c90z4305z89fbz91449bbbdbdc
Projection mapping based on BRDF reconstruction from single RGBD image
Xun, L., Xiao, S., Bian, C., & Jiang, J. (2018) · ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry (VRCAI) · doi:10.1145/3284398.3284410
“While DynamicFusion [Newcombe et al. 2015] proposed a system to reconstruct moving objects and dynamic scenes by RGBD scans.”
BackgroundBednarek, M., & Walas, K. (2018) · Signal Processing: Algorithms, Architectures, Arrangements, and Applications · doi:10.23919/spa.2018.8563402
“real-time approach of reconstructing dynamic scenes was presented in [12].”
BackgroundLearning shape spaces of dressed 3D human models in motion
Yang, J. (2019) · theses.fr (ABES) · doi:10.70675/abd9b226z9389z4ca0z9b93z833e9d22f183
3D Body and Background Reconstruction in a Large-scale Indoor Scene using Multiple Depth Cameras
Kobayashi, D., Thomas, D., Uchiyama, H., & Taniguchi, R.-I. (2019) · Asia Pacific Workshop on Mixed and Augmented Reality (APMAR) · doi:10.1109/apmar.2019.8709280
“In 2015, Newcombe et.al. presented DynamicFusion [3], the first system that is capable of reconstructing non-rigid 3D shapes in real-time with a RGB-D camera.”
BackgroundInfluentialA Spatio-Temporal-Contour-Consistency-Based Shape Tracking Framework from Multi-View Video
Huang, C., Qin, J., & Li, Z. (2019)
Representation of Uncertain Occupancy Maps with High Level Feature Vectors
Arukgoda, J., Ranasinghe, R., & Dissanayake, G. (2019) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2019.8842965
“Although truncated SDF is widely used to match point clouds[11][12], clearly defining regions as ’inside’ or ’outside’ in a complex environment is difficult, and sometimes impossible.”
Background3D Non-rigid Registration of Deformable Object Using GPU
Lee, J., Kim, E.-S., & Park, S.-Y. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-31332-6_53
A Motion Capture System for Sport Performance Analysis Based on Inexpensive RGB-D Sensors
ANDRE, C., LEMAITRE, C., Voiry, M., & Lavault, A. (2019) · International Conference on 3D Body Scanning Technologies (3DBST) · doi:10.15221/19.176
Vision-based multi-sensor fusion for robust unmanned aerial vehicles autonomous navigation
Yuan, S. (2019) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/85185
Dynamic Human Body 3D Reconstruction using Laplacian Deformation
Bian, Q., & Zhang, G. (2019) · IEEE Data Driven Control and Learning Systems Conference (DDCLS) · doi:10.1109/ddcls.2019.8908869
“Similar to DynamicFusion [7], volumetric representation is used to represent the initial scene and deformation in this paper.”
BackgroundMethodInfluentialStudy of a Method for Effective Noise Suppression in Passive Personnel Screening Systems
Zhuravlev, A. V. (2019) · IEEE International Conference on Microwaves, Communications, Antennas and Electronic Systems (COMCAS) · doi:10.1109/comcas44984.2019.8958181
“The KinectFusion method was further improved in the DynamicFusion method [7], in which a scene with moving and deformable objects is reconstructed in real-time using the same RGB-D video sensor.”
MethodFine-tuning SMPL: A Framework for Highly Detailed Statistical Human Model Building
Patakin, N., Ilia, P., Vladimir, G. S., & Konushin, A. (2019) · International Conference on Video, Signal and Image Processing (VSIP) · doi:10.1145/3369318.3369335
“Recent advances in 3D reconstruction methods allow capturing of human body shape and pose from lower cost setups such as one [1], [13] or few RGB cameras [8] or one depth sensor [19], [12].”
BackgroundFast and Accurate 4D Modeling of Large Multi-Camera Sequences
Leroy, V. (2019) · theses.fr (ABES) · doi:10.70675/7e4f0cd2z4927z4484z8e93z02b80362072c
Zampogiannis, K., Ganguly, K., Fermuller, C. M., & Aloimonos, Y. (2020) · Springer eBooks · doi:10.1007/978-3-030-46732-6_9
Template-Based Hand Shape Recovery from a Single Depth Image
Fan, Q., Shen, X., Tang, B., & Lyu, G. (2019) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv47840.2019.00012
“Follow up work [15] further capable of reconstructing non-rigidly deforming scenes in real-time, but can not address drift problem with dynamic motion.”
BackgroundResultNon-rigid 3D reconstruction of the human body in motion
Elanattil, S. (2020) · Queensland University of Technology · doi:10.5204/thesis.eprints.205095
Zhuravlev, A. V., Razevig, V. V., Chizh, M. A., Ge, D., & Boxiong, H. (2020) · International Radar Symposium · doi:10.23919/irs48640.2020.9253959
“The recent advances in computer vision methods that allow tracking and reconstruction of deformable shapes, such as DynamicFusion [9], VolumeDeform [10], DensePose [11], and others, let us hope that the concealed object tracking error could be made sufficiently small for animate bodies, not greater than a couple of ce…”
MethodResearch on 3D Reverse Technology Based on Monocular Image Sequence
Chen, Y., Xu, J., Feng, W., Yuan, H., Gu, H., & Han, Y. (2021) · International Conference on Artificial Intelligence and Information Systems (ICAIIS) · doi:10.1145/3469213.3470679
“…are defined by pairs of feature pairs, then the initial slices are made as close as possible to the tangent plane of the surface of the object to be reconstructed, and the grayscale consistency function is used to determine the optimal value of the slices in this space determined by the pairs [22].”
MethodRegistration Techniques for Deformable ObjectsPreprint
Ahmadi, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.04053
“The regularization term assigns a cost between node i and node j which are connected by an edge [37].”
BackgroundMethodInfluentialRao, G. R. K., Anupama, V., Bharadwaj, A. A., & Prasad, C. H. V. K. (2021) · International Conference on Electronics, Communication and Aerospace Technology (ICECA) · doi:10.1109/iceca52323.2021.9676025
“The conceptual design will be focused on the development of the 3D software reconstruction for a 3D scanner[14].”
Method(2021) · Elsevier eBooks · doi:10.1016/b978-0-12-821343-8.00030-7
State-of-the-Art Sensors Technology in Spain 2017
Martinsanz, G. (2018) · MDPI eBooks · doi:10.3390/books978-3-03842-914-2 · Cited by 1
Non-rigid Tracking Using RGB-D Data
Petit, A., Lippiello, V., & Siciliano, B. (2022) · Springer tracts in advanced robotics · doi:10.1007/978-3-030-93290-9_2
Improvement of Dense 3D Reconstruction System Based on Depth Camera
Li, M., Zhang, Y., & Guo, T. (2021) · International Conference on Video and Image Processing (ICVIP) · doi:10.1145/3511176.3511198
A non-rigid dynamic scene reconstruction method based on surface element model
Jiang, Y. D., Zeng, Y., Du, J., & Fei, W. (2021) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio54168.2021.9739502
Maier, R. L., & Cremers, D. (2020) · Springer eBooks · doi:10.1007/978-3-642-41610-1_109-1
Fast 3D Reconstruction of Human Figures in Motion
Nasir, T. (2018) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2018-13395
DR-Fusion: Dynamic SLAM 3D Reconstruction Method of Production Workshop
Gou, R., Chen, G., Pu, X., & Zuo, T. (2022) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai55851.2022.9904280
“DynamicFusion [12] builds a model by detecting the state of the object in the input depth map.”
BackgroundPyramidal Signed Distance Learning for Spatio-Temporal Human Shape Completion
Zhou, B., Franco, J.-S., Gorce, M. D. L., & Boyer, E. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26319-4_22
“Dynamic fusion approaches [31,17] are another classical set of approaches that are neither model-based nor regression-based and which consist in tracking point cloud correspondences, aligning point cloud in a non-rigid manner and fusing the aligned point clouds into a single surface representation.”
3D face alignment and face reconstruction based on image sequence
Yao, W., Qiao, B., Wang, H., Zhang, M., Liu, S., & Tao, L. (2022) · International Conference on Digital Image Processing · doi:10.1117/12.2644477
“Therefore, some work has begun to use CNN to estimate 3D deformation model coefficient(3DMM) 4 or 3D model distortion function 6,7 to recover corresponding 3D information from a single 2d face image, thus providing dense face alignment and 3D face reconstruction results.”
MethodaSDF: Reconstructing Real-Time Signed Distance Fields with Enhanced Attention
Maxim, B., & Nedevschi, S. (2022) · IEEE International Conference on Intelligent Computer Communication and Processing (ICCP) · doi:10.1109/iccp56966.2022.10053972
“Truncated SDFs have commonly been used in traditional SLAM systems [7], [8], but since it has been applied to room-scale representations [9].”
MethodSmartVP: Viewpoint Optimization Based on Individual Preference for Watching 3D Boxing Punch Videos
Tao, T., Ratsamee, P., Liu, C., Uranishi, Y., & Takemura, H. (2023) · International Conference on Image, Video and Signal Processing (IVSP) · doi:10.1145/3591156.3591171
“However, there are some research and technology about 3D reconstruction for humans with depth data [7, 13].”
BackgroundOnline Consistent Video Depth with Gaussian Mixture Representation
Liu, C., Eckart, B., & Kautz, J. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160785
“Our method focuses on the online scene level reconstruction for RGB video input where the measured dense maps are not available [21], [37], [36], [55].”
Method
Metadata
- Authors
- Newcombe, R. A., Fox, D., & Seitz, S. M.
- Affiliations
- University of Washington (US)
- Venue
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2015-06
- Pages
- 343-352
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W1938204631
- Cited by
- 951
- References
- 42
- Citations by year
- 2026: 28 · 2025: 61 · 2024: 67 · 2023: 93 · 2022: 84 · 2021: 113 · 2020: 105 · 2019: 124 · 2018: 110 · 2017: 78 · 2016: 80 · 2015: 8
- FWCI
- 159.57
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Keywords
- dense SLAM, real-time 3D reconstruction, KinectFusion
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.