REMODE: Probabilistic, monocular dense reconstruction in real time
Open accessThe DOI matches its Crossref record; 25 of the 26 references it cites were found in a registry or an index.
Abstract
In this paper, we solve the problem of estimating dense and accurate depth maps from a single moving camera. A probabilistic depth measurement is carried out in real time on a per-pixel basis and the computed uncertainty is used to reject erroneous estimations and provide live feedback on the reconstruction progress. Our contribution is a novel approach to depth map computation that combines Bayesian estimation and recent development on convex optimization for image processing. We demonstrate that our method outperforms state-of-the-art techniques in terms of accuracy, while exhibiting high efficiency in memory usage and computing power. We call our approach REMODE (REgularized MOnocular Depth Estimation). Our CUDA-based implementation runs at 30Hz on a laptop computer and is released as open-source software.
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
“These representations have recently gained popularity in monocular SLAM, in conjunction with the use of direct methods [118, 184, 203], which estimate the trajectory of the robot and a 3D model directly from the intensity values of all the image pixels.”
From Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016) · cites this paper as [203]
Citations
Cites
Multiple View Geometry in Computer Vision
Hartley, R., & Zisserman, A. (2004) · doi:10.1017/cbo9780511811685 · Cited by 21,070
Nonlinear total variation based noise removal algorithms
Rudin, L. I., Osher, S., & Fatemi, E. (1992) · Physica D: Nonlinear Phenomena · doi:10.1016/0167-2789(92)90242-f · Cited by 15,704
A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging
Chambolle, A., & Pock, T. (2011) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-010-0251-1 · Cited by 4,336
Accurate, Dense, and Robust Multiview Stereopsis
Furukawa, Y., & Ponce, J. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.161 · Cited by 3,019
A 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×
“The growing interest for dense reconstructions has renewed the attention in multi-view stereo techniques [3], [4], [5], [6], where the involved computational complexity used to prevent applications in robot perception.”
BackgroundSVO: Fast semi-direct monocular visual odometry
Forster, C., Pizzoli, M., & Scaramuzza, D. (2014) · 2014 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2014.6906584 · Cited by 2,205
Self-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 · cited 4×
“If, on one hand, estimating the depth independently for every pixel leads to efficient, parallel implementations, on the other hand the authors of [10], [11], [12] argued that, similar to other computer vision problems, such as image de-noising [13] and optical flow estimation [14], a smoothing step is required in ord…”
BackgroundMethodInfluentialReal-time simultaneous localisation and mapping with a single camera
Davison (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238654 · Cited by 1,733
Fast Global Minimization of the Active Contour/Snake Model
Bresson, X., Esedoḡlu, S., Vandergheynst, P., Thiran, J.-P., & Osher, S. (2007) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-007-0002-0 · Cited by 857
Inverse Depth Parametrization for Monocular SLAM
Civera, J., Davison, A. J., & Montiel, J. (2008) · IEEE Transactions on Robotics · doi:10.1109/tro.2008.2003276 · Cited by 779
Research works printed but not linked: 1
- werlberger, 0, Motion estimation with nonlocal total variation regularization, Proc IEEE Conf on Computer Vision and Pattern Recognition 2010
Cited by
Items 301–330 of 330
Modelling of Terrain Surfaces Using Aerial Radar Mapping
Murdoch, D., Ye, E., Shaker, G. S. A., & Melek, W. (2018) · Journal of Computational Vision and Imaging Systems
Scale Invariant Multi-view Depth Estimation Network with cGAN Refinement
Yeh, C., Huang, Y.-P., & Chen, M. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-9190-3_75
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
Efficient and Robust 3D Object Reconstruction Based on Monocular SLAM and CNN Semantic Segmentation
Weber, T., Triputen, S., Gopal, A., Eißler, S., Höfert, C., Schreve, K., & Rätsch, M. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-35699-6_27
Gareau, D. (2019) · UWSpace (University of Waterloo)
Samiksha: Low Cost Field Monitoring System
Srivastava, S., Garg, A., Verma, R., & Prabhakar, T. V. (2018) · International Conference on Recent Innovations in Electrical, Electronics & Communication Engineering (ICRIEECE) · doi:10.1109/icrieece44171.2018.9008472
“This app is also provided with five pre-build surveillance patterns which are configured to operate over 1-3 acer of square or rectangle fields [11, 12, 13, 14, 15].”
MethodDeep Learning Assisted Visual Odometry
Tang, J. (2020) · KTH Publication Database DiVA (KTH Royal Institute of Technology)
A Front-End for Dense Monocular SLAM using a Learned Outlier Mask PriorPreprint
Zhang, Y., & Leonard, J. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.00562
“In [25], this measurement uncertainty is obtained by assuming a”
BackgroundMethod3OFRR-SLAM: Visual SLAM with 3D-Assisting Optical Flow and Refined-RANSAC
Zhai, Y., Tang, F.-L., & Wu, Y. (2021) · Asian Conference on Pattern Recognition · doi:10.1007/978-3-031-02375-0_11
“In the tracking thread, they extract FAST [19] corners and track them using the direct method while using a depth filter [18] to recover the depths.”
MethodShariq, M. H., & Hughes, B. R. (2022) · Proceedings of the International Conference on Evolving Cities · doi:10.55066/proc-icec.2021.30
“Thankfully, monocular photogrammetry provides a timeefficient real-time solution to 3D model reconstruction through series of images captured with overlapping features [8, 9].”
BackgroundFast and robust visual SLAM for dynamic environments
Gaurav, S. (2022) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/155251 · Cited by 1
Visual Slam-Based Mapping and Localization for Aerial Images
Eker, O., Çevıkalp, H., & Sarıbaş, H. (2022) · Journal of Engineering Research and Sciences · doi:10.55708/js0101001
“In [11], the authors proposed a dense monocular reconstruction method that integrates SVO as camera pose estimation”
MethodLeveraging deep-learned object detectors for real-world semantic localization and mapping
Nicholson, L. (2023) · Queensland University of Technology · doi:10.5204/thesis.eprints.242733 · Cited by 2
IVI-SLAM: Tracking, Mapping by Internal Video Inpainting for Dynamic Scene
Hua, C., Liu, G., Zhang, W., & Zhang, H. (2024) · Frontiers in artificial intelligence and applications · doi:10.3233/faia240143
Map Completion for SLAM Systems Based on Neural Radiance Field
Deng, S., Zuo, W., Xia, Y., Xin, J., Zhou, S., & Zheng, N. (2023) · China Automation Congress (CAC) · doi:10.1109/cac59555.2023.10450787
Autonomous Navigation Algorithm of Monocular UAV Based on Depth Estimation and Robust VIO
Zhen, X., Deng, Z., Lou, B., Hou, L., & Wei, L. (2024) · International Forum on Electrical Engineering and Automation (IFEEA) · doi:10.1109/ifeea64237.2024.10878697 · Cited by 1
Fast Intrinsic–Extrinsic Calibration for Pose-Only Structure-from-Motion
Tian, X., Ge, Y., Tan, Z., Chen, X., Li, M., & Hu, D. (2025) · Remote Sensing · doi:10.3390/rs17132247
Real-Time AGV Localization and Dense 3D Map Reconstruction Using Visual SLAM
Wang, W., Hao, L., & Wang, Y. (2025) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber67662.2025.11168379
“Despite advancements in dense SLAM algorithms like DTAM (Dense Tracking And Mapping) [10] and REMODE (REgularized MOnocular Depth Estimation) [11], their computational complexity and hardware demands hinder real-time AGV deployment.”
Research on Rotating SAR 3D Imaging Method Based on Bayesian Estimation
Dong, J., Lin, Y., Wang, Y., Shen, W., Li, Y., & Jiang, W. (2025) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss55030.2025.11242705
“Consequently, depth computation can be formulated as Bayesian probabilistic estimation[13].”
Direct Monocular Visual SLAM: Variants and Extensions
Poorna, M., Raj, A., Adamsab, K., & O, P. M. (2025) · International Conference on Electronic Circuits and Signaling Technologies (ICECST) · doi:10.1109/icecst66106.2025.11307364
“Recent advances aim to enhance robustness, scale recovery, and drift mitigation under challenging real-world conditions [5], [6], [7], [11], [13]: 1) Scale-aware Monocular Odometry with Deep Learning Integration Deep neural networks predict monocular depth maps to address scale ambiguity and drift.”
InfluentialARGM: Arial Robust Geo-Mapping
Li, Z., Xue, J., & Kang, L. (2025) · International Conference on Computer, Big Data and Artificial Intelligence (ICCBD+AI) · doi:10.1109/iccbdai66607.2025.11387939
“OpenRealm [6] and Hinzmann et al. [18] use dense reconstruction [19], [20] for orthomosaics.”
FollowFusion: Online MVS for Terrain Adaptive Viewpoint Generation
Xia, Z., Chen, L., Han, P., & Bu, S. (2025) · Asian Aerospace and Astronautics Conference (AAAC) · doi:10.1109/aaac66612.2025.11427426
“[ 21] generate real-time paths for continuous scene exploration and real-time reconstruction based on the REMODE [22] and Cas-MVSNet methods, respectively.”
Super résolution de texture pour la reconstruction 3D fine
Burns, C. (2018) · theses.fr (ABES) · doi:10.70675/61266807z3f12z4afcza3aczd1ea2b5050df
Gohard, P.-A. (2018) · theses.fr (ABES) · doi:10.70675/d90fc3e3zd301z43d6zac80z5a16f803431f · Cited by 1
Mennillo, L. (2019) · theses.fr (ABES) · doi:10.70675/d169246ezfdeaz4ea9z81e2z0f0d378bfc45 · Cited by 2
Decentralized monocular-inertial multi-UAV SLAM system
Spaenlehauer, A. (2019) · theses.fr (ABES) · doi:10.70675/9884414ez8196z42caz8968zd7d2ea4e391e
Dubois, R. (2021) · theses.fr (ABES) · doi:10.70675/7c156bfaze487z4eeczbc6fz5e4cc0a88493 · Cited by 1
Effective Gaussian Management for High-Fidelity Scene Reconstruction
Liu, J., Gao, H., Xie, J.-C., Pun, C., Xiong, J., Li, H., Chen, J., & Xu, F. (2026) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2026.3705489
“Recently, neural implicit and explicit representations, most notablyneuralradiancefields(NeRF)and3DGaussianSplatting (3DGS),haveadvancedthestateoftheartinviewsynthesisand scenereconstruction.”
Depth Refinement with Sparse Geometry for Agricultural and Forest Scenes
Zhong, Z., Xu, S., Coombes, M., & Liu, C. (2026) · International Conference on Automation and Computing (ICAC) · doi:10.1109/icac70325.2026.11712435
“For better depth quality, some refinement strategies apply smoothness constraints to the depth/disparity image, either during optimisation [27] or after estimation [28].”
Metadata
- Authors
- Pizzoli, M., Forster, C., & Scaramuzza, D.
- Affiliations
- University of Zurich (CH)
- ORCID
- Scaramuzza, Davide
- Venue
- 2014 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2014-05
- Pages
- 2609-2616
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2093659073
- Cited by
- 330
- References
- 26
- Citations by year
- 2026: 3 · 2025: 11 · 2024: 10 · 2023: 16 · 2022: 26 · 2021: 33 · 2020: 36 · 2019: 48 · 2018: 39 · 2017: 47 · 2016: 33 · 2015: 20 · 2014: 8
- FWCI
- 19.36
- Type
- conference paper
- Language
- en
- Open access
- green
- www.zora.uzh.ch
- Licence
- other-oa
- Locations
- Proceedings - IEEE International Conference on Robotics and Automation/Proceedings (publishedVersion)
- Zurich Open Repository and Archive (University of Zurich) (acceptedVersion, other-oa)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Zurich Open Repository and Archive (University of Zurich) (submittedVersion, other-oa)
- Zurich Open Repository and Archive (University of Zurich)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Engineering › Media Technology › Image Processing Techniques and Applications
- Keywords
- monocular depth estimation, dense reconstruction, uncertainty estimation, Bayesian estimation, convex optimization, real-time depth estimation, CUDA
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.