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 901–956 of 956
Rohner, D., Hartwig, J., & Henrich, D. (2023) · Springer eBooks · doi:10.1007/978-3-031-10071-0_23
Real-Time Dynamic Full Scene Reconstruction Using a Heterogeneous Sensor System
Finnie, S. (2023) · Open Access Victoria University of Wellington | Te Herenga Waka (Figshare) · doi:10.26686/wgtn.24268960
Body Posture Detection Based on OpenPose and 3D Reconstruction
Mai, Y., Xu, R., Luo, Q., & Zhang, Z. (2023) · Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC) · doi:10.1109/ipec57296.2023.00021
“Such as ColMap[5], SFM[6], SLAM[7], KinectFusion[8], ElasticFusion[9], DynamicFusion[10], etc.”
Dynamic 3D Reconstruction using Moving Depth Camera Mounted on Robotic Arm
Mai, H., Chen, X., Chang, L., & Yang, L. (2023) · International Conference on Robotics and Automation Engineering (ICRAE) · doi:10.1109/icrae59816.2023.10458577
“Dynamic-Fusion of Newcombe et al. [8] first present dense reconstruction system capable of reconstructing non-rigidly deforming scenes in real-time with no required of static scene assumption, which also proposes a novel approach to volumetric 6D warp field.”
BackgroundHuman Body 3D Measurement Method and Application Based on Human Body Model—SMPL
刘, 寒. (2024) · Modeling and Simulation · doi:10.12677/mos.2024.132112
Fast Correspondence Clustering by Cluster-Wise Spatial Compatibility for Point Cloud Registration
Liu, C., Zhang, Y., Xu, Z., & Ma, J. (2023) · International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) · doi:10.1109/cei60616.2023.10528088
Depth Guided Fast Rendering Neural Radiance Fields
Zhang, T., & Wang, H. (2024) · Conference on Fully Actuated System Theory and Applications (FASTA) · doi:10.1109/fasta61401.2024.10595382
“Some studies[28] have focused on integrating correlational information between frames in dynamic scenes, gradually refining and detailing the reconstructed models by inputting newly captured data into keyframe models.”
BackgroundBlender-NeRF: A Monocular Dynamic Human Body Explicit Reconstruction and Rendering Method
Chen, S., Liu, W., Yan, B., Sang, X., Li, A., & Yi, X. (2024) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew63481.2024.10645469
“DynamicFusion [10] reconstructs the geometric shape of the scene while simultaneously estimating dense volumetric 6D motion fields, which warp the estimated geometry to the live frame.”
BackgroundRapid 3D Reconstruction of E-commerce Product Scenes Based on Neural Radiance Fields
Deng, K. (2024) · Smart innovation, systems and technologies · doi:10.1007/978-981-97-5184-6_11
Budria, A., Lopez-Rodriguez, A., Lorente, Ò., & Moreno-Noguer, F. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0960-4_16
Liang, Z., Guo, W., Yang, Y., & Liu, T. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0972-7_4
“Some works require extensive depth cameras [1], LiDAR [26], cameras and optical flow input [7].”
Towards Finer Human Reconstruction for Single RGB-D Images
Zhu, Y. P., Yu, Q., Dai, R., Wang, L., Liu, Z., & Fang, X. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-82021-2_9
Adaptable Deep Learning Based Depth Refinement for Infrared Stereo Camera
Liu, B., An, L., Chi, P., Zhao, J., Tao, C., & Wang, Y. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-2204-7_6
3D Geometry and Semantic Reconstruction
Yang, X., Yin, B., & Wei, X. (2025) · Springer eBooks · doi:10.1007/978-981-96-3177-3_1
An Elastic Fine-Tuning Dual Recurrent Framework for Non-Rigid Point Cloud Registration
Yuan, M., Li, X., & Tan, H. (2025) · Sensors · doi:10.3390/s25113525 · Cited by 1
“…differ by bending and stretching) alignment to minimize the distance between surfaces with regular expressions, such as Tukey, Welsch, and Geman– McCLure, which corrects the registration process in terms of smoothness, point location, Sensors 2025 , 25 , 3525 2 of 21 local topology, etc. [9–11].”
Non-Volumetric Dynamic Reconstruction With Adaptive Correction
Luo, J., Liu, X., Ma, X., Han, S., & Kuang, H. (2025) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit65432.2025.11035734
“Traditional real-time dynamic scene reconstruction typically follows the DynamicFusion [5] standard pipeline, constructing a canonical model and solving sparse non-rigid deformation to warp the model from the canonical field into the live field, then incrementally updating the model based on…”
PrIF: Point-Related Implicit Function for Single View Clothed Human Reconstruction
Gao, Y., Yu, W. D., & Gao, H. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-6462-7_3
ReDACT: Reconstructing Detailed Avatar with Controllable Texture
Chen, Z., Zhu, H., Luo, F., & Xiao, C. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-0100-7_5
Mono2VR: Exploring Immersive Experiences of Monocular VideosPreprint
Dickson, A., Lo, W. H., Schrimper, F., Knott, A., Ventura, J., & Zollmann, S. (2025) · Research Square · doi:10.21203/rs.3.rs-7302128/v1
Toward Scalable, Flexible Scene Flow for Point CloudsPreprint
Vedder, K. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.15666
ModelNet40-E: An Uncertainty-Aware Benchmark for Point Cloud ClassificationPreprint
Alonso, P., Li, T., & Li, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.01269
Capturing Head Avatar with Hand Contacts from a Monocular Video
He, H., Zheng, Y., & Song, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01217
“Early meth-ods, such as DynamicFusion [16] and KinectFusion [11], estimate a template-free 6D motion field to warp live frames into a TSDF surface.”
Monocular Endoscopic Tissue 3D Reconstruction with Multi-Level Geometry Regularization
Chen, Y., & Wang, H. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227925
“All these methods track deformation based on a sparse warp field [21], which is not robust when deformations are significantly beyond the scope of non-topological changes.”
GS-Morph: Dynamic Novel View Synthesis via UDF-ARAP Gaussian Splat Morphing
Belemkoabga, D.-S., Maugey, T., & Guillemot, C. M. (2025) · Conference on Visual Media Production · doi:10.1145/3756863.3769701
“Systems like PointFusion [10], DynamicFusion [17], and BundleFusion [2] fuse geometry over time but assume limited deformation and static scenes.”
Qi, W., & Zhang, C. (2025) · IEEE Access · doi:10.1109/access.2025.3631914
“Dynamic feature fusion (DFF) has achieved remarkable success in various vision tasks, including semantic segmentation [26], [28], object detection, and image aesthetic evaluation [40].”
CORNet: A Consistency-based Outlier Rejection Network for non-rigid registration
Yu, C. Y., Zhang, S., & Shen, L. (2025) · Computer-Aided Design · doi:10.1016/j.cad.2025.103980
LOD-InfiniTAM: Adaptive Depth Sampling for Accurate RGB-D SLAM
Zhang, T., Li, N., Gong, G., Tian, B., & Lin, X. (2025) · International Conference on Robotics and Computer Vision (ICRCV) · doi:10.1109/icrcv67407.2025.11349343
“In response, a series of follow-up efforts have emerged, aiming to enhance mapping scalability [4], support dynamic environments [5], improve memory efficiency [6], and strengthen dense alignment robustness [8].”
Wang, Y., & Kambhamettu, C. (2025) · IEEE International Conference on Image Processing Workshops (ICIPW) · doi:10.1109/icipw68931.2025.11386030
“A significant break-through came with DynamicFusion [7], which directly and simultaneously recovers geometry and non-rigid motion in real time by jointly optimizing a canonical shape and a per-frame deformation field.”
InfluentialReconstructing Dynamic Scenes with Topologically-Varying Neural Implicit Fields
Wang, K., Zhao, M., & Li, S.-Y. (2026) · CSIAM Transactions on Applied Mathematics · doi:10.4208/csiam-am.so-2025-0064
“Previous reconstruction systems rely on expensive multi-camera studios [4,11,20,27, 28] that prevent their daily applications or require depth sensors [8, 14, 36, 37, 39] for high-quality 3D reconstruction which cannot be applied when 3D data is unavailable.”
Melbouci, K. (2017) · theses.fr (ABES) · doi:10.70675/f064ee62z857bz4254za1dcz64a9b99b0c18 · Cited by 1
Hybrid Machine Learning and Geometric Approaches for Single RGB Camera Relocalization
Duong, N.-D. (2019) · theses.fr (ABES) · doi:10.70675/8e4ecee4z215fz435az93aez8cb46cfd16fa · Cited by 1
Jiddi, S. (2019) · theses.fr (ABES) · doi:10.70675/386eff80z6b53z49a2zb0f6z44502f0a95ee
“Consequently, proposed approaches within this task such as [Newcombe et al., 2015] could be considered.”
MethodThree-dimension facial de-ageing and ageing Modeling : extrinsic factors impact
Heravi, F. M. Z. (2019) · theses.fr (ABES) · doi:10.70675/58fe2ebdz1e0cz4dfdzae73zcae3d7ef812b
Visual SLAM for humanoid robot localization and closed-loop control
Tanguy, A. (2018) · theses.fr (ABES) · doi:10.70675/c1de38eazd63bz466azaad1z00a1f0f5a847
Director: Instance-Aware Gaussian Splatting for Dynamic Scene Modeling and Understanding
Jiang, Y., Cai, Y., Wang, Z., Wu, Y., Li, S., Su, Z., Jiao, S., & Xu, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37447-9_7
Real-time scene analysis for 3D interaction
Kaiser, A. (2019) · theses.fr (ABES) · doi:10.70675/3f01cf2bzae9cz4996z99adz1ac064278490 · Cited by 1
Inferring Dense Human Representation from Sparse or Incomplete Point Clouds
Zhou, B. (2022) · theses.fr (ABES) · doi:10.70675/4320f05dz1203z47c8z9440z930e935cdc53
Shape tracking and servoing of deformable objects
Bushehri, S. M. S. (2023) · theses.fr (ABES) · doi:10.70675/92f0ba7ez3eabz4393za6dcza7485bac7135
Vision-based robotic dual arm manipulation of soft objects
Saghour, C. (2023) · theses.fr (ABES) · doi:10.70675/0f34f763z4c09z4aeeza2b8z4b2f7476c580
3D As‐Built Environments in Extended Reality Applications: A Systematic Review
Balado, J., Feng, Y., Qiu, Z., Gao, W., & Julin, A. (2026) · The Photogrammetric Record · doi:10.1111/phor.70046
Deep Local Field Consistency for Non-Rigid Point Cloud Registration
Xu, H., Li, C. J., Lu, C., Zhang, D. H., & Zhu, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462853
MaLCA: Point Cloud Registration with Mamba-Enhanced Features and Local Correspondence Augmentation
Huo, Y., Zhang, L., Guo, H., Gong, J., Kuang, L., Han, X., & Xiong, F. (2026) · Algorithms · doi:10.3390/a19050380
Too Tiny to See: Hazardous Obstacle Detection Dataset and Evaluation
Miekkala, T., Brucker, S., Walz, S., Ghilotti, F., Ramazzina, A., Scheuble, D., Pyykönen, P., Bijelic, M., & Heide, F. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00184
“These methods enable dense scene understanding across a wide range of applications including robotics [53, 56], autonomous driving [16, 67, 73], and augmented reality [52, 57, 78].”
Energy-based Body Reconstruction from Sparse Image Sequences using Single Depth Camera
Qiu, J., & Kundur, D. (2025) · International Conference on Smart Multimedia (ICSM) · doi:10.1109/icsm64417.2025.11541472
“DynamicFusion [9] generalizes this for applications in dynamic, largely non-rigid scenes.”
Han, D., Zhang, F.-C., Gu, R., Zhang, F., & Wang, M. (2026) · Computer Graphics Forum · doi:10.1111/cgf.70508
Zisu, S., & Butnariu, S. (2026) · Sensors · doi:10.3390/s26134007
JacobianAvatar: Temporally Consistent Semi-rigid Avatar Reconstruction from a Monocular Video
Won, C., Park, M., Park, S. J., Yoon, J. H., & Jeon, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37013-6_34
Implicit Surface Compression -- with Good Old Discrete Cosine Transform and Motion Compensation
Jin, T., Wu, S., Huang, T., Dasari, M., Seshan, S., & Rowe, A. (2026) · ACM Transactions on Graphics · doi:10.1145/3811298
“Template-free reconstruction methods such as DynamicFusion [Newcombe et al. 2015] and ElasticFusion [Whelan et al. 2015b] maintain an evolving canonical model using warp fields or deformation graphs [Sumner et al. 2007], often with as-rigid-as-possible regularization [Igarashi et al. 2005; Sorkine…”
FuzzyGS: Fuzzy-Based Geometric Uncertainty Gaussian Splatting for Fast Talking Head Synthesis
Lv, X., Shao, M., Liu, C. Y., Meng, L., Qiao, Y., Wan, Y., & Chen, X. S. (2026) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2026.3710187
“Following [40], [41], the updated Gaussian positions μ i can be calculated as where R k and T k denote the rotation matrix and translation vector of neighbor G k , respectively.”
ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation
Wu, J., Liang, J., Hu, D., Yang, J., Xiong, K., Li, X., Zheng, X., Wang, C., & Wang, R. (2026) · ACM Transactions on Graphics · doi:10.1145/3811306
“Early approaches relied heavily on strong priors, such as shape-from-silhouette techniques [Ahmed et al. 2008], deformable template models [Carranza et al. 2003], or template-free dynamic reconstruction systems augmented with depth sensors [Newcombe et al. 2015].”
Globally Consistent Non-rigid Map Fusion for MASt3R-SLAM
Feng, Y., Yu, C., Zhang, B., Liu, Y., Ran, F., & Wang, Y. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-9938-7_26
Cai, Z., Liu, X., Li, S., Li, X., & Shang, W. (2026) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma69663.2026.11647338
“Volumetric non-rigid fusion methods, such as DynamicFusion [3] and VolumeDeform [4], optimize deformation fields over a fused volume and repeatedly integrate depth observations.”
Minute4D: Training High-Fidelity 4D Gaussian Splatting in One Minute
Xie, B., Shi, C., Zhang, P., & Wu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37464-6_7
Tele360: Real-Time Feed-forward Human Reconstruction from Sparse Unposed Cameras
Tu, H., Liao, Z., Min, W., Zhang, J., & Liu, Y. (2026) · ACM Transactions on Graphics · doi:10.1145/3842578
A Survey of Map Construction and Management Methods for Single Embodied Agents
Yan, C., Feng, Z., Ye, F., Sun, Y., Gong, Y., & Liu, Y. (2026) · Sensors · doi:10.3390/s26196242
Xie, P., Wu, G., & 崔, 达. (2026) · Machines · doi:10.3390/machines14111233
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.