Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM
Open accessAbstract
We present Co-SLAM, a neural RGB-D SLAM system based on a hybrid representation, that performs robust camera tracking and high-fidelity surface reconstruction in real time. Co-SLAM represents the scene as a multi-resolution hash-grid to exploit its high convergence speed and ability to represent high-frequency local features. In addition, Co-SLAM incorporates one-blob encoding, to encourage surface coherence and completion in unobserved areas. This joint parametric-coordinate encoding enables real-time and robust performance by bringing the best of both worlds: fast convergence and surface hole filling. Moreover, our ray sampling strategy allows Co-SLAM to perform global bundle adjustment over all keyframes instead of requiring keyframe selection to maintain a small number of active keyframes as competing neural SLAM approaches do. Experimental results show that Co-SLAM runs at 10-17Hz and achieves state-of-the-art scene reconstruction results, and competitive tracking performance in various datasets and benchmarks (ScanNet, TUM, Replica, Synthetic RGBD). Project page: https://hengyiwang.github.io/projects/CoSLAM
Integrity signals
Registry
Cites
Statistics
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?
DeeR-VLA optimizes reasoning with dynamic early-exit mechanism to reduce computational overhead.
“Efficient alignment of multimodal features is critical, with OpenVLA [19] using Low-Rank Adaptation (LoRA) for parameter-efficient fusion, while DeeR-VLA [155] optimizes reasoning with a dynamic early-exit mechanism to reduce computational overhead.”
From Multimodal fusion and vision–language models: A survey for robot vision (2026) · cites this paper as [155]
Cites
ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras
Mur-Artal, R., & Tardos, J. D. (2017) · IEEE Transactions on Robotics · doi:10.1109/tro.2017.2705103 · Cited by 6,898 · see citing works
NeRF: representing scenes as neural radiance fields for view synthesis
Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2022) · Communications of the ACM · doi:10.1145/3503250 · Cited by 6,852 · see citing works
Instant neural graphics primitives with a multiresolution hash encoding
Müller, T., Evans, A., Schied, C., & Keller, A. (2022) · ACM Transactions on Graphics · doi:10.1145/3528223.3530127 · Cited by 6,584 · see citing works
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
Dai, A., Chang, A. X., Savva, M., Halber, M., Funkhouser, T., & Niessner, M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.261 · Cited by 4,368 · see citing works
A benchmark for the evaluation of RGB-D SLAM systems
Sturm, J., Engelhard, N., Endres, F., Burgard, W., & Cremers, D. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385773 · Cited by 4,098 · see citing works
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 · see citing works
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 · see citing works
Plenoxels: Radiance Fields without Neural Networks
Fridovich-Keil, S., Yu, A., Tancik, M., Chen, Q., Recht, B., & Kanazawa, A. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00542 · Cited by 1,418 · see citing works
Efficient Geometry-aware 3D Generative Adversarial Networks
Chan, E. R., Lin, C. Z., Chan, M. A., Nagano, K., Pan, B., Mello, S. D., Gallo, O., Guibas, L. J., Tremblay, J., Khamis, S., et al. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01565 · Cited by 1,118 · see citing works
Real-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 1,001 · see citing works
Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction
Sun, C. G., Sun, M., & Chen, H.-T. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00538 · Cited by 956 · see citing works
NICE-SLAM: Neural Implicit Scalable Encoding for SLAM
Zhu, Z., Peng, S., Larsson, V., Xu, W., Bao, H., Cui, Z., Oswald, M. R., & Pollefeys, M. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01245 · Cited by 865 · see citing works
ElasticFusion: Dense SLAM Without A Pose Graph
Whelan, T., Leutenegger, S., Salas Moreno, R., Glocker, B., & Davison, A. (2015) · Robotics: Science and Systems XI · doi:10.15607/rss.2015.xi.001 · Cited by 835 · see citing works
CNN-SLAM: Real-Time Dense Monocular SLAM with Learned Depth Prediction
Tateno, K., Tombari, F., Laina, I., & Navab, N. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.695 · Cited by 800 · see citing works
The Replica Dataset: A Digital Replica of Indoor SpacesPreprint
Straub, J., Whelan, T. J., Ma, L., Chen, Y., Wijmans, E., Green, S., Engel, J. J., Mur-Artal, R., Ren, C. Y., Verma, S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.05797 · Cited by 711 · see citing works
ElasticFusion: Real-time dense SLAM and light source estimation
Whelan, T. J., Salas-Moreno, R. F., Glocker, B., Davison, A. J., & Leutenegger, S. (2016) · The International Journal of Robotics Research · doi:10.1177/0278364916669237 · Cited by 694 · see citing works
iMAP: Implicit Mapping and Positioning in Real-Time
Sucar, E., Liu, S., Ortiz, J., & Davison, A. J. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00617 · Cited by 693 · see citing works
Kintinuous: 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 590 · see citing works
Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes
Takikawa, T., Litalien, J., Yin, K., Kreis, K., Loop, C., Nowrouzezahrai, D., Jacobson, A., McGuire, M., & Fidler, S. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01120 · Cited by 450 · see citing works
D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
Yang, N., von Stumberg, L., Wang, R., & Cremers, D. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00136 · Cited by 438 · see citing works
BAD SLAM: Bundle Adjusted Direct RGB-D SLAM
Schöps, T., Sattler, T., & Pollefeys, 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.2019.00022 · Cited by 388 · see citing works
DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D CamerasPreprint
Teed, Z., & Deng, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.10869 · Cited by 360 · see citing works
Müller, T., McWilliams, B., Rousselle, F., Groß, M. H., & Novák, J. (2019) · ACM Transactions on Graphics · doi:10.1145/3341156 · Cited by 321 · see citing works
The Embedding Hypothesis: From Fourier Circuits to No-Q AttentionPreprint
Rigoni, N. (2026) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.19273886 · Cited by 304 · see citing works
Very High Frame Rate Volumetric Integration of Depth Images on Mobile Devices
Kähler, O., Prisacariu, V. A., Ren, C. Y., Sun, X., Torr, P. H. S., & Murray, D. W. (2015) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2015.2459891 · Cited by 294 · see citing works
Neural RGB-D Surface Reconstruction
Azinović, D., Martin-Brualla, R., Goldman, D. B., NieBner, M., & Thies, J. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00619 · Cited by 292 · see citing works
Scalable real-time volumetric surface reconstruction
Chen, J., Bautembach, D., & Izadi, S. (2013) · ACM Transactions on Graphics · doi:10.1145/2461912.2461940 · Cited by 247 · see citing works
Dai, A., Nießner, M., Zollhöfer, M., Izadi, S., & Theobalt, C. (2017) · ACM Transactions on Graphics · doi:10.1145/3072959.3126814 · Cited by 211 · see citing works
MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface ReconstructionPreprint
Yu, Z., Peng, S., Niemeyer, M., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.00665 · Cited by 164 · see citing works
Neural 3D Scene Reconstruction with the Manhattan-world Assumption
Guo, H., Peng, S., Lin, H., Wang, Q., Zhang, G., Bao, H., & Zhou, X. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00543 · Cited by 162 · see citing works
Octree-based fusion for realtime 3D reconstruction
Zeng, M., Zhao, F., Zheng, J., & Liu, X. (2012) · Graphical Models · doi:10.1016/j.gmod.2012.09.002 · Cited by 121 · see citing works
Efficient Octree-Based Volumetric SLAM Supporting Signed-Distance and Occupancy Mapping
Vespa, E., Nikolov, N., Grimm, M., Nardi, L., Kelly, P. H. J., & Leutenegger, S. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2792537 · Cited by 117 · see citing works
ReLU Fields: The Little Non-linearity That Could
Karnewar, A., Ritschel, T., Wang, O., & Mitra, N. J. (2022) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3528233.3530707 · Cited by 87 · see citing works
GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction
Wang, J., Bleja, T., & Agapito, L. (2022) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv57658.2022.00055 · Cited by 75 · see citing works
Self-citationVox-Surf: Voxel-Based Implicit Surface Representation
Li, H., Yang, X., Zhai, H., Liu, Y., Bao, H., & Zhang, G. (2022) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2022.3225844 · Cited by 66 · see citing works
Voxurf: Voxel-based Efficient and Accurate Neural Surface ReconstructionPreprint
Wu, T., Wang, J., Pan, X., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2208.12697 · Cited by 31 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
RD-VIO: Robust visual-inertial odometry for mobile augmented reality in dynamic environments
Li, J., Pan, X., Huang, G., Zhang, Z., Wang, N., Bao, H., & Zhang, G. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3353263 · Cited by 62 · see citing works
“NICE-SLAM [53], Vox-Surf [22], Vox-Fusion [49] and the latest ESLAM [19], Co-SLAM [47] are typical neural implicit SLAM methods.”
MethodMultimodal fusion and vision–language models: A survey for robot vision
Han, X., Chen, S., Fu, Z., Feng, Z., Fan, L., An, D., Wang, C., Guo, L., Meng, W., Zhang, X., et al. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103652 · Cited by 41 · see citing works
“Such pre-training not only enables better handling of multimodal data but also enhances the model’s overall performance in complex applications [183].”
- Authors
- Wang, H., Wang, J., & Agapito, L.
- Affiliations
- University College London (GB)
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 13293-13302
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386066696
- Cited by
- 287
- References
- 36
- Citations by year
- 2026: 64 · 2025: 133 · 2024: 84 · 2023: 6
- FWCI
- 151.81
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- UCL Discovery (University College London) (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- Cisco Systems
- UK Research and Innovation (EP/S021566/1)
- Engineering and Physical Sciences Research Council (EP/T022205/1, EP/S021566/1, T022205/1)
- Topics
- Physical Sciences › Engineering › Aerospace Engineering › Robotics and Sensor-Based Localization
- Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Keywords
- RGB-D SLAM, camera tracking, surface reconstruction, ray sampling, bundle adjustment, real-time SLAM, keyframe selection
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
