DTAM: Dense tracking and mapping in real-time
The DOI matches its Crossref record; 16 of the 17 references it cites were found in a registry or an index.
Abstract
DTAM is a system for real-time camera tracking and reconstruction which relies not on feature extraction but dense, every pixel methods. As a single hand-held RGB camera flies over a static scene, we estimate detailed textured depth maps at selected keyframes to produce a surface patchwork with millions of vertices. We use the hundreds of images available in a video stream to improve the quality of a simple photometric data term, and minimise a global spatially regularised energy functional in a novel non-convex optimisation framework. Interleaved, we track the camera's 6DOF motion precisely by frame-rate whole image alignment against the entire dense model. Our algorithms are highly parallelisable throughout and DTAM achieves real-time performance using current commodity GPU hardware. We demonstrate that a dense model permits superior tracking performance under rapid motion compared to a state of the art method using features; and also show the additional usefulness of the dense model for real-time scene interaction in a physics-enhanced augmented reality application.
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
“However, in our network, multi-scale projections not only help to overcome gradient locality during training (see [33], [47] for a broader discussion of this well-known issue), but also aid in online error correction at runtime.”
From Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery (2020) · cites this paper as [33]
In the citing paper
“SFMLearner [33] demonstrated the unsupervised learning of unscaled egomotion and depth from RGB imagery.”
From Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery (2020) · cites this paper as [33]
In the citing paper
“For KITTI, VIOLearner RGB outperforms approaches SFMLearner [33] and the network of Zhan et al. [30].”
From Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery (2020) · cites this paper as [33]
In the citing paper
“For AirSim, VIOLearner (no IMU) outperforms approaches SFMLearner [33] and ORB-SLAM2-S in translation error.”
From Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery (2020) · cites this paper as [33]
In the citing paper
“Compared to other vision-only approaches, for KITTI, VIOLearner (no IMU) outperforms approaches SFMLearner [33] and the network of Zhan et al. [30] and yet is outperformed by ORB-SLAM-2 which uses full bundle adjustment.”
From Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery (2020) · cites this paper as [33]
Citations
Cites
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
Parallel 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
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
Lucas-Kanade 20 Years On: A Unifying Framework
Baker, S., & Matthews, I. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000011205.11775.fd · Cited by 3,155
Fast cost-volume filtering for visual correspondence and beyond
Rhemann, C., Hosni, A., Bleyer, M., Rother, C., & Gelautz, M. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995372 · Cited by 485
Live dense reconstruction with a single moving camera
Newcombe, R. A., & Davison, A. J. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539794 · Cited by 366
Self-citationImproving the Agility of Keyframe-Based SLAM
Klein, G., & Murray, D. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88688-4_59 · Cited by 335
Robust multi-sensor image alignment
Irani, M., & Anandan, P. (2002) · Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271) · doi:10.1109/iccv.1998.710832 · Cited by 220
Real-Time Dense Geometry from a Handheld Camera
Stühmer, J., Gumhold, S., & Cremers, D. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15986-2_2 · Cited by 205
Some First-Order Algorithms for Total Variation Based Image Restoration
Aujol, J. (2009) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-009-0149-y · Cited by 151
Cited by
Items 401–500 of 1,004
Research on SLAM Algorithm of Mobile Robot Based on the Fusion of 2D LiDAR and Depth Camera
Mu, L., Yao, P., Zheng, Y., Chen, K., Wang, F., & Qi, N. (2020) · IEEE Access · doi:10.1109/access.2020.3019659 · Cited by 55
“VSLAM then entered a period of rapid development and a large number of excellent algorithmic frameworks emerged, ORB-SLAM [22], [23], DTAM [24], LSD-SLAM [25]–[27], SVO [28] and DVO-SLAM [29].”
BackgroundRobust Tracking for Real-Time Dense RGB-D Mapping with Kintinuous
Whelan, T. J., Johannsson, H., Kaess, M., Leonard, J. J., & McDonald, J. (2012) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 54
RGBDTAM: A cost-effective and accurate RGB-D tracking and mapping system
Concha, A., & Civera, J. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206593 · Cited by 55
Enhancing Self-Supervised Monocular Depth Estimation with Traditional Visual Odometry
Andraghetti, L., Myriokefalitakis, P., Dovesi, P. L., Luque, B., Poggi, M., Pieropan, A., & Mattoccia, S. (2019) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00054 · Cited by 54
“Large progress has been achieved in the development of VO and SLAM methods [9, 10, 31, 32].”
MethodVOLDOR: Visual Odometry From Log-Logistic Dense Optical Flow Residuals
Min, Z., Yang, Y., & Dunn, E. (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/cvpr42600.2020.00495 · Cited by 59
“Conversely, direct methods [58, 16, 45], strive to jointly determine a (semi-)dense registration (warping) across images, as well as the parameters of a camera motion model.”
BackgroundMethodLeveraging Planar Regularities for Point Line Visual-Inertial Odometry
Li, X., He, Y., Lin, J., & Liu, X. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341278 · Cited by 54
“In [4], [5] dense mapping can be realized based on monocular vision and pixel-wise reconstruction, which is time-consuming and highly relies on Graphics Processing Unit (GPU) to guarantee real-time performance.”
BackgroundConvolutional networks for real-time 6-DOF camera relocalization.Preprint
Kendall, A., Grimes, M. K., & Cipolla, R. (2015) · arXiv (Cornell University) · Cited by 50
Zhong, M., Hong, C., Jia, Z., Wang, C., & Wang, Z. (2024) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2024.104634 · Cited by 52
Robust vision-aided navigation using Sliding-Window Factor graphs
Chiu, H.-P., Williams, S., Dellaert, F., Samarasekera, S., & Kumar, R. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630555 · Cited by 59
“The same parallelization is also used in more recent works [7].”
MethodDense 3D Reconstruction from Severely Blurred Images Using a Single Moving Camera
Lee, H. S., & Lee, K. M. (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.2013.42 · Cited by 53
“In the proposed method, camera motion is estimated by image registration method between a reference image and an warped observed image using a reconstructed depth map, similarly to other 3D reconstruction algorithms [16].”
BackgroundMethodIntrinsic Depth: Improving Depth Transfer with Intrinsic Images
Kong, N., & Black, M. J. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.401 · Cited by 50
“[21, 32]).”
Video-Based Outdoor Human Reconstruction
Zhu, H., Liu, Y., Fan, J., Dai, Q., & Cao, X. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2596118 · Cited by 51
“Inspired by the monocular dense tracking method [7], we extract matching information from the input video/images to overcome the instability of the outdoor scenes.”
MethodInfluentialIndoor positioning and obstacle detection for visually impaired navigation system based on LSD-SLAM
Endo, Y., Sato, K., Yamashita, A., & Matsubayashi, K. (2017) · International Conference on Biometrics and Kansei Engineering (ICBAKE) · doi:10.1109/icbake.2017.8090635 · Cited by 47
“LSD-SLAM is based on direct visual odometry (DVO) [4][5], and the environmental map is represented by a graph structure, so that a graph 2017 International Conference on Biometrics and Kansei Engineering”
MethodReal-Time CPU-Based Large-Scale Three-Dimensional Mesh Reconstruction
Piazza, E., Romanoni, A., & Matteucci, M. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2800104 · Cited by 59
Multirobot Collaborative Monocular SLAM Utilizing Rendezvous
Jang, Y., Oh, C., Lee, Y.-W., & Kim, H. J. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3058502 · Cited by 53
Direct semi-dense SLAM for rolling shutter cameras
Kim, J.-H., Cadena, C., & Reid, I. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487263 · Cited by 46
“Direct SLAM approaches, which use dense textured maps and photometric based image warping (in contrast to landmark based approaches) have been introduced [17], [4].”
BackgroundNeuromorphic vision: From sensors to event‐based algorithms
Annamalai, L., Chakraborty, A., & Thakur, C. S. (2019) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1310 · Cited by 59
“vious run of dense standard reconstruction approaches of CMOS camera such as DTAM (Newcombe et al., 2011) or”
MethodInfluentialSensors and Sensor Fusion Methodologies for Indoor Odometry: A Review
Yang, M., Sun, X. S., Jia, F., Rushworth, A. G. A., Dong, X., Zhang, S., Fang, Z., Yang, G., & Liu, B. (2022) · Polymers · doi:10.3390/polym14102019 · Cited by 55
“The regional-matching-based methods recover the transformation by minimizing the photometric error function, and have been implemented for stereo cameras [215–218], RGB-D cameras [219], and monocular cameras in dense [220], semi-dense [221], and sparse [222,223] fashion.”
BackgroundMethodVisual SLAM algorithms and their application for AR, mapping, localization and wayfinding
Theodorou, C., Velisavljević, V., Dyo, V., & Nonyelu, F. (2022) · Array · doi:10.1016/j.array.2022.100222 · Cited by 60
Appearance-based Active, Monocular, Dense Reconstruction for Micro Aerial Vehicles
Förster, C., Pizzoli, M., & Scaramuzza, D. (2014) · Robotics: Science and Systems · doi:10.15607/rss.2014.x.029 · Cited by 53
“When observing demonstrations of monocular dense reconstruction from hand-held cameras, such as [17, 19], one can notice the commonly used pattern of moving the camera in a circular trajectory around a reference view.1 Intuitively, a circular trajectory constitutes a reasonable approach, as the…”
BackgroundMethodHandling pure camera rotation in keyframe-based SLAM
Pirchheim, C., Schmalstieg, D., & Reitmayr, G. (2013) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2013.6671783 · Cited by 47
“SLAM systems with six degrees of freedom (6DOF) [6, 7, 11, 15] assume general camera motion and apply structure-from-motion techniques to create 3D feature maps.”
MethodCombining Inertial Navigation and ICP for Real-time 3D Surface Reconstruction
Nießner, M., Dai, A., & Fisher, M. (2014) · Eurographics · doi:10.2312/egsh.20141003 · Cited by 55
“One approach is to use visual SLAM (simultaneous localization and mapping) [Dav03, KM07, KRD08, NLD11].”
MethodA SMARTPHONE-BASED 3D PIPELINE FOR THE CREATIVE INDUSTRY – THE REPLICATE EU PROJECT
Nocerino, E., Lago, F., Morabito, D., Fabio Remondino, A., Porzi, L., Poiesi, F., Bulò, S. R., Chippendale, P., Locher, A., Havlena, M., et al. (2017) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xlii-2-w3-535-2017 · Cited by 46
“…work on real-time 3D reconstruction has come from Pollefeys et al. (2008), Vogiatzis and Hernandez (2011), Wendel et al. (2012) and Pradeep et al. (2013) whereas works on real-time tracking and mapping were presented in Klein and Murray (2009), Stuehmer et al. (2010) and Newcombe et al. (2011).”
BackgroundRobust SLAM system based on monocular vision and LiDAR for robotic urban search and rescue
Chen, X., Zhang, H., Lu, H., Xiao, J., Qiu, Q., & Li, Y. (2017) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr.2017.8088138 · Cited by 53
“[7], [8]).”
Edge-SLAM: edge-assisted visual simultaneous localization and mapping
Ben Ali, A. J., Hashemifar, Z. S., & Dantu, K. (2020) · Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3386901.3389033 · Cited by 46
Shu, F., Lesur, P., Xie, Y., Pagani, A., & Stricker, D. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00180 · Cited by 58
Multimodal sensor-based semantic 3D mapping for a large-scale environment
Jeong, J., Yoon, T. S., & Park, J. B. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.03.051 · Cited by 52
A Review of Recurrent Neural Network Based Camera Localization for Indoor Environments
Alam, M. S., Mohamed, F., Selamat, A., & Hossain, A. B. (2023) · IEEE Access · doi:10.1109/access.2023.3272479 · Cited by 52
“Dense Tracking and Mapping: The concept of Dense Tracking and Mapping (DTAM) was first forth by Newcombe et al. [180].”
BackgroundGround Truth Data, Content, Metrics, and Analysis
Krig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5_7 · Cited by 52
UniVIO: Unified Direct and Feature-Based Underwater Stereo Visual-Inertial Odometry
Miao, R., Qian, J., Yang, S. S., Ying, R., & Liu, P. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3136259 · Cited by 58
“The dense methods, such as dense tracking and mapping (DTAM) [10] and large-scale direct monocular SLAM (LSD-SLAM) [11], require enormous computational resources.”
MethodHigh-Definition Map Representation Techniques for Automated Vehicles
Soorchaei, B. E., Razzaghpour, M., Valiente, R., Raftari, A., & Fallah, Y. P. (2022) · Electronics · doi:10.3390/electronics11203374 · Cited by 60
LVIO-Fusion:Tightly-Coupled LiDAR-Visual-Inertial Odometry and Mapping in Degenerate Environments
Zhang, H., Du, L., Bao, S., Yuan, J., & Ma, S. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3371383 · Cited by 54
“The early direct VO method like DTAM [14], estimates camera states by aligning the whole image with the dense depth map.”
MethodDeng, T., Wang, Y., Xie, H., Wang, H., Guo, R., Wang, J., Wang, D., & Chen, W. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3541064 · Cited by 55
“For learning-based SLAM systems, DTAM [5] is one of the pioneer works that use the dense map and view-centric scene representation.”
Approximated user-perspective rendering in tablet-based augmented reality
冨岡, 誠., Ikeda, S., & Sato, K. (2013) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2013.6671760 · Cited by 44
“Even if a dense 3D surface can be obtained, the effects of smoothness regularization [8] and measurement errors may locally distort the displayed real images.”
BackgroundDirect visual odometry for a fisheye-stereo camera
Liu, P., Heng, L., Sattler, T., Geiger, A., & Pollefeys, M. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8205988 · Cited by 53
“In contrast, direct visual odometry methods [16] attempt per-pixel depth estimation, and thus, require the use of a commodity GPU for real-time”
BackgroundBayesian DeNet: Monocular Depth Prediction and Frame-Wise Fusion With Synchronized Uncertainty
Yang, X. Y., Gao, Y., Luo, H., Liao, C., & Cheng, K.-T. T. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2912121 · Cited by 48
A non-rigid map fusion-based direct SLAM method for endoscopic capsule robots
Turan, M., Almalıoğlu, Y., Araújo, H. J., Ender Konukoglu, A., & Sitti, M. (2017) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-b-000236254 · Cited by 44
Overview of deep learning application on visual SLAM
Li, S., Zhang, D., Xian, Y., Li, B., Zhang, T., & Zhong, C. (2022) · Displays · doi:10.1016/j.displa.2022.102298 · Cited by 54
Playing Doom with SLAM-Augmented Deep Reinforcement Learning
Bhatti, S., Desmaison, A., Mikšík, O., Nardelli, N., Siddharth, N., & Torr, P. H. S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.00380 · Cited by 43
“A more complete map representation is provided by dense approaches [41, 34, 27].”
BackgroundStructure from motion using dense CNN features with keypoint relocalization
Widya, A. R., Torii, A., & Okutomi, M. (2018) · IPSJ Transactions on Computer Vision and Applications · doi:10.1186/s41074-018-0042-y · Cited by 52
“In VisualSLAM approaches, namely, LSD-SLAM [43] and DTAM [44] repeat camera pose estimation based on selected keyframe and (semi-)dense reconstruction using the pixel-level correspondences in real-time.”
MethodA comprehensive overview of dynamic visual SLAM and deep learning: concepts, methods and challenges
Beghdadi, A., & Mallem, M. (2022) · Machine Vision and Applications · doi:10.1007/s00138-022-01306-w · Cited by 56
“DTAM [66] 2011 Monocular Direct – Dense – – – n/a”
MethodInfluentialGe, Y., Zhang, L., Wu, Y., & Hu, D. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3366815 · Cited by 52
“The former used a direct method to optimize camera poses [15] by minimizing the photometric error between consecutive frames, whereas the latter used an indirect method to optimize camera poses and the map by minimizing the reprojection error between consecutive frames.”
MethodLive tracking and mapping from both general and rotation-only camera motion
Gauglitz, S., Sweeney, C., Ventura, J., Turk, M., & Höllerer, T. (2012) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2012.6402532 · Cited by 52
“Therefore, the robustness of the 3D mapping part can currently not compete with the robustness demonstrated by systems such as PTAM [14] or DTAM [22].”
BackgroundMethodResultInfluentialSibbing, D., Sattler, T., Leibe, B., & Kobbelt, L. P. (2013) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2013.16 · Cited by 44
“Most similar to our approach are the works of Gee & Mayol-Cuevas and Newcombe et al. [7], [17].”
ResultReal-Time 3D Tracking and Reconstruction on Mobile Phones
Prisacariu, V. A., Kähler, O., Murray, D. W., & Reid, I. D. (2014) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2014.2355207 · Cited by 42
“The established method for rendering a 3D shape represented in such a way is to use a raycasting algorithm [9].”
BackgroundMethodInfluentialArticulated Robot Motion for Simultaneous Localization and Mapping (ARM-SLAM)
Klingensmith, M., Sirinivasa, S. S., & Kaess, M. (2016) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2016.2518242 · Cited by 53
“Examples include LSD-SLAM [6] and DTAM [22].”
Tian, G., Liu, L., Ri, J., Liu, Y., & Sun, Y. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.088 · Cited by 45
“Depending on the different type of input data being processed, SLAM can be divided into either monocular camera-based [16–18] or depth camera-based [6,19,20] .”
BackgroundDeepAVO: Efficient pose refining with feature distilling for deep Visual Odometry
Zhu, R., Yang, M., Liu, W., Song, R., Yan, B., & Xiao, Z. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.09.029 · Cited by 50
Overview of Multi-Robot Collaborative SLAM from the Perspective of Data Fusion
Chen, W., Wang, X., Gao, S., Shang, G., Zhou, C., Li, Z., Xu, C., & Hu, K. (2023) · Machines · doi:10.3390/machines11060653 · Cited by 61
Fast and effective online pose estimation and mapping for UAVs
Schneider, J., Eling, C., Klingbeil, L., Kuhlmann, H., Förstner, W., & Stachniss, C. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487682 · Cited by 42
“As our evaluation shows, we provide accurate pose estimates at the given frequencies, we can handle underconstrained GPS situations well, and the resulting 3D models are accurate and georeferenced.”
MethodAutonomous aerial robot using dual‐fisheye cameras
Gao, W., Wang, K., Ding, W., Gao, F., Qin, T., & Shen, S. (2020) · Journal of Field Robotics · doi:10.1002/rob.21946 · Cited by 51
DRIO: Robust Radar-Inertial Odometry in Dynamic Environments
Chen, H., Liu, Y., & Cheng, Y. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3301290 · Cited by 43
“Over the years, visual odometry (VO) [1], [2], [3], [4], [5] and Lidar odometry (LO) [6], [7] have attracted great interest and achieved encouraging outcomes.”
BackgroundMethodVisual SLAM for Unmanned Aerial Vehicles: Localization and Perception
Zhuang, L., Zhong, X., Xu, L., Tian, C., & Yu, W. (2024) · Sensors · doi:10.3390/s24102980 · Cited by 56
“DTAM [69] uses a keyframe-based framework to construct a dense depth map by minimizing the global photometric error, requiring only an RGB sensor and commodity GPU hardware.”
Method6D Relocalisation for RGBD Cameras Using Synthetic View Regression
Gee, A. P., & Mayol-Cuevas, W. W. (2012) · British Machine Vision Conference (BMVC) · doi:10.5244/c.26.113 · Cited by 41
“Maps of this kind can nowadays be built in real-time with commodity hardware using single cameras [11, 15] or RGBD sensors [9, 14].”
BackgroundOptical-flow based self-supervised learning of obstacle appearance applied to MAV landing
Ho, H. W., Wagter, C. D., Remes, B. D. W., & de Croon, G. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.10.004 · Cited by 42
“The direct method tries to avoid this limit ation by using image intensities directly to generate (semi-) den se maps ([14], [15], [16]).”
MethodCollaborative Visual SLAM Using Compressed Feature Exchange
Opdenbosch, D. V., & Steinbach, E. G. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2878920 · Cited by 49
“Representatives of both direct and dense methods are the Dense Tracking and Mapping (DTAM) [3] and LargeScale Direct SLAM (LSD SLAM) [4].”
MethodA Survey on Time-of-Flight Stereo Fusion
Nair, R., Ruhl, K., Lenzen, F., Meister, S., Schäfer, H., Garbe, C. S., Eisemann, M., Magnor, M. A., & Kondermann, D. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-44964-2_6 · Cited by 51
“If the fusion system is moving and the scene mostly static, it is possible to use structure from motion (SFM) techniques [21,22] to additionally infer depth at some locations.”
BackgroundNaseer, F., Khan, M. N., & Altalbe, A. A. (2023) · Sustainability · doi:10.3390/su15043585 · Cited by 43
SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion
Wu, S.-C., Tateno, K., Navab, N., & Tombari, F. (2020) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv50981.2020.00090 · Cited by 53
“Research activities in real-time dense 3D reconstruction can be subdivided between depth-based [34, 17] and monocular [35, 37, 50].”
BackgroundSemantic Visual Simultaneous Localization and Mapping: A Survey
Chen, K., Xiao, J., Liu, J., Tong, Q., Zhang, H., Liu, R., Zhang, J., Ajoudani, A., & Chen, S. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3556928 · Cited by 61
“Direct tracking methods, such as DTAM [29] and LSD-SLAM [30], eliminate the need for feature extraction and matching.”
FARLAP: Fast robust localisation using appearance priors
Pascoe, G., Maddern, W., Stewart, A. D., & Newman, P. M. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7140093 · Cited by 40
“This provides richer information about the scene than simply using a pointcloud, as shown by [4].”
BackgroundMethodInfluentialDense RGB-D visual odometry using inverse depth
Gutiérrez-Gómez, D., Mayol-Cuevas, W. W., & Guerrero, J. J. (2015) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2015.09.026 · Cited by 42
“Thus WA(p) becomes an unknown yielding an ill-posed problem with WimHim constraints for WimHim+6 unknowns, which is solved using optical flow variational methods [36], or by performing variable baseline stereo matching [11].”
BackgroundMethodTowards Autonomous Navigation of Miniature UAV
Brockers, R., Humenberger, M., Weiß, S., & Matthies, L. H. (2014) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2014.98 · Cited by 49
“Since t can only be estimated up to scale from a monocular setup, we use the pose information from our pose estimator to scale the translation vector.”
MethodSuperpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scene
Kumar, S., Dai, Y., & Li, H. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2955131 · Cited by 54
Improving Monocular Visual Odometry Using Learned Depth
Sun, L., Yin, W., Xie, E., Li, Z., Sun, C., & Shen, C. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3164834 · Cited by 48
“Visual odometry and simultaneous localization and mapping (SLAM) [9], [39], [40], [41], [42], [43], [44] are of great importance for robot navigation and mobile vision applications.”
ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild
Zhao, W., Liu, S., Guo, H., Wang, W., & Liu, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19824-3_31 · Cited by 101
Meilland, M., Comport, A. I., & Rives, P. (2014) · Journal of Field Robotics · doi:10.1002/rob.21531 · Cited by 43
“To ensure a better initialisation, a direct registration technique is employed to estimate the local inter-frame 3D rotation of the camera as in (Mei et al., 2010; Lovegrove and Davison, 2010; Newcombe et al., 2011b).”
MethodEfficient minimal-surface regularization of perspective depth maps in variational stereo
Graber, G., Balzer, J., Soatto, S., & Pock, T. (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.2015.7298649 · Cited by 43
“The majority of variational methods resort to implicit handling of depth discontinuities by TV regularization [15] [26] [25] [34] [40] .”
BackgroundOnline Dense Non-Rigid 3D Shape and Camera Motion Recovery
Agudo, A., Montiel, J. M. M., Agapito, L., & Calvo, B. (2014) · British Machine Vision Conference (BMVC) · doi:10.5244/c.28.107 · Cited by 39
Efficient multi-camera visual-inertial SLAM for micro aerial vehicles
Houben, S., Quenzel, J., Krombach, N., & Behnke, S. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759261 · Cited by 42
“Dense methods like DTAM [3] estimate for each pixel a depth value and often rely on massive hardware parallelization via GPUs to obtain real-time capabilities.”
MethodPiao, J.-C., & Kim, S. (2017) · Sensors · doi:10.3390/s17112567 · Cited by 47
“The dense tracking and mapping DTAM [20] reconstructs the surrounding map information into a dense 3D depth map model.”
MethodUnDEMoN: Unsupervised Deep Network for Depth and Ego-Motion Estimation
Babu, V. M., Das, K., Majumdar, A., & Kumar, S. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593864 · Cited by 45
MagicVO: An End-to-End Hybrid CNN and Bi-LSTM Method for Monocular Visual Odometry
Jiao, J., Jiao, J., Mo, Y., Liu, W., & Deng, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2926350 · Cited by 58
Wen, S., Zhao, Y., Liu, X., Sun, F., Lu, H., & Wang, Z. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.3041852 · Cited by 41
“There are two predominant visual-inertial system methods: monocular visual-inertial sys-tem [24]–[26] and stereo visual-inertial system [27], [28].”
MethodEnd-to-End RGB-D SLAM With Multi-MLPs Dense Neural Implicit Representations
Li, M., He, J., Wang, Y., & Wang, H. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3311365 · Cited by 47
Review on SLAM algorithms for Augmented Reality
Sheng, X., Mao, S., Yan, Y., & Yang, X. (2024) · Displays · doi:10.1016/j.displa.2024.102806 · Cited by 58
How NeRFs and 3-D Gaussian Splatting Are Reshaping SLAM: A Survey
Tosi, F., Zhang, Y., Gong, Z., Sandström, E., Mattoccia, S., Oswald, M. R., & Poggi, M. (2026) · IEEE Transactions on Robotics · doi:10.1109/tro.2026.3666139 · Cited by 141
“At the outset, hand-crafted algorithms [2], [10], [25], [26], [27] demonstrated remarkable real-time performance and scalability.”
BackgroundP-HRTF: Efficient personalized HRTF computation for high-fidelity spatial sound
Meshram, A., Mehra, R., Yang, H., Dunn, E., Franm, J.-M., & Manocha, D. (2014) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2014.6948409 · Cited by 48
A Survey of Simultaneous Localization and Mapping.
Huang, B., Zhao, J., & Liu, J. (2019) · Cited by 53
A mapping of visual SLAM algorithms and their applications in augmented reality
Covolan, J. P. M., Sementille, A. C., & Sanches, S. R. R. (2020) · Symposium on Virtual and Augmented Reality (SVR) · doi:10.1109/svr51698.2020.00019 · Cited by 42
“14) KinectFusion: Em Newcombe et al. [25], é apresentado o KinectFusion.”
BackgroundLeast Commitment, Viewpoint-Based, Multi-view Stereo
Hu, X., & Mordohai, P. (2012) · International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission · doi:10.1109/3dimpvt.2012.60 · Cited by 43
“Impressive results have been achieved in real-time using robust regularization on the cost volume of a single reference image [29, 37, 30].”
BackgroundLai, T. (2022) · Sensors · doi:10.3390/s22197265 · Cited by 55
“For example, DTAM [68], LSD-SLAM [69] and SVO [70] are some of the models that had gain lots of successes.”
BackgroundInteractive 3D Model Acquisition and Tracking of Building Block Structures
Miller, A. E., White, B., Charbonneau, E., Kanzler, Z., & LaViola, J. J. (2012) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2012.48 · Cited by 44
“Finally, we note that some 3D acquisition systems use color images instead of (or in addition to) depth images [7, 18, 25].”
BackgroundJoint prediction of depths, normals and surface curvature from RGB images using CNNs
Dharmasiri, T., Spek, A., & Drummond, T. W. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8205954 · Cited by 36
“Prior to the resurgence of neural networks depth was either computed using a Simultaneous Localisation and Mapping (SLAM) system [24], [2] or directly obtained from a range sensor such as expensive LIDAR, stereo rigs, Time of Flight (ToF) sensors or structured light sensors[25] (Microsoft Kinect).”
MethodFrom the Calibration of a Light-Field Camera to Direct Plenoptic Odometry
Zeller, N., Quint, F., & Stilla, U. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2017.2737965 · Cited by 38
“Here, tracking and dense mapping can be performed in one step, as shown in [17].”
MethodDRM-SLAM: Towards dense reconstruction of monocular SLAM with scene depth fusion
Ye, X., Ji, X., Sun, B., Chen, S., Wang, Z., & Li, H. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.02.044 · Cited by 41
A visual SLAM-based bronchoscope tracking scheme for bronchoscopic navigation
Wang, C., Oda, M., Hayashi, Y., Villard, B., Kitasaka, T., Takabatake, H., Mori, M., Honma, H., Natori, H., & Mori, K. (2020) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-020-02241-9 · Cited by 37
“Due to the fact that dense SLAM [20,21] uses image pixels directly, which may either be influenced by illumination or be computationally demanding, we selected a featurepoint-based SLAM scheme, monocular ORB-SLAM [22], for bronchoscope tracking after a comprehensive investigation of existing visual SLAM frameworks.”
MethodReview of Visual Simultaneous Localization and Mapping Based on Deep Learning
Zhang, Y., Wu, Y., Tong, K., Chen, H., & Yuan, Y. (2023) · Remote Sensing · doi:10.3390/rs15112740 · Cited by 42
Evaluating dual-view perceptual issues in handheld augmented reality
Pucihar, K. Č., Coulton, P., & Alexander, J. (2013) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/2522848.2522885 · Cited by 36
A Unified Rolling Shutter and Motion Blur Model for 3D Visual Registration
Meilland, M., Drummond, T. W., & Comport, A. I. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.252 · Cited by 36
“The RS deformation is observable when there is parallax between two successive scan-lines due to motion.”
BackgroundFast Reconstruction of 3D Point Cloud Model Using Visual SLAM on Embedded UAV Development Platform
Huang, F., Yang, H., Tan, X., Peng, S., Tao, J., & Peng, S. (2020) · Remote Sensing · doi:10.3390/rs12203308 · Cited by 40
“Progress has also been made [53,54] in improving the robustness of SLAM by predicting the depths of pixels and extracting image blocks.”
BackgroundNeural Free-Viewpoint Performance Rendering under Complex Human-object Interactions
Sun, G., Chen, X., Chen, Y., Pang, A., Lin, P., Jiang, Y., Xu, L., Yu, J., & Wang, J. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475442 · Cited by 48
“Classical multi-view stereo reconstruction approaches [12, 14, 41, 54] and recent neural rendering approaches [30, 36, 64] rely on”
BackgroundVIO-DualProNet: Visual-inertial odometry with learning based process noise covariance
Solodar, D., & Klein, I. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108466 · Cited by 42
“In recent years, many simultaneous localization and mapping (SLAM) techniques were developed, leveraging a variety of sensors, including stereo cameras [1], [2], [3], LiDAR [4], [5], [6], depth cameras [7], [8], ultra white-band sensors [9], [10], and magnetic sensors [11].”
BackgroundTracking an RGB-D Camera Using Points and Planes
Ataer-Cansızoğlu, E., Taguchi, Y., Ramalingam, S., & Garaas, T. W. (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.14 · Cited by 39
“SLAM systems using a single 2D camera [7, 11, 12, 14] are generally successful for textured scenes, but encounter many failure modes with texture-less regions.”
BackgroundDense multibody motion estimation and reconstruction from a handheld camera
Roussos, A., Russell, C., Garg, R., & Agapito, L. (2012) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2012.6402535 · Cited by 40
Fast and Adaptive 3D Reconstruction With Extensively High Completeness
Wu, P., Liu, Y., Ye, M., Li, J., & Du, S. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2612761 · Cited by 38
“real-time augmented reality by tracking the full 6-DOF camera position [4] and computer-assisted laparoscopic surgery [5] by reconstructing 3D tissue surface.”
MethodSparse sensing for resource-constrained depth reconstruction
Ma, F., Carlone, L., Ayaz, U., & Karaman, S. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759040 · Cited by 35
“A variety of approaches has been proposed to perform geometry reconstruction using these sensors, see [1], [2], [3] and the references therein.”
BackgroundKrig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5_2 · Cited by 44
LSTM and Filter Based Comparison Analysis for Indoor Global Localization in UAVs
Yusefi, A., Durdu, A., Aslan, M. F., & Sungur, C. (2021) · IEEE Access · doi:10.1109/access.2021.3049896 · Cited by 37
Interest Point Detector and Feature Descriptor Survey
Krig, S. (2016) · Springer eBooks · doi:10.1007/978-3-319-33762-3_6 · Cited by 44
Metadata
- Authors
- Newcombe, R. A., Lovegrove, S. J., & Davison, A. J.
- Affiliations
- Imperial College London (GB)
- ORCID
- Davison, Andrew J.
- Venue
- 2011 International Conference on Computer Vision
- Publisher
- IEEE
- Published
- 2011-11
- Pages
- 2320-2327
- OpenAlex
- W2108134361
- Cited by
- 2,078
- References
- 17
- Citations by year
- 2026: 49 · 2025: 144 · 2024: 163 · 2023: 140 · 2022: 141 · 2021: 166 · 2020: 179 · 2019: 199 · 2018: 183 · 2017: 176 · 2016: 136 · 2015: 151 · 2014: 102 · 2013: 92 · 2012: 51
- FWCI
- 154.56
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Earth and Planetary Sciences › Geology › 3D Surveying and Cultural Heritage
- Keywords
- dense 3D reconstruction, real-time mapping, depth images, non-convex optimization, energy minimization, image registration, GPU parallelization, augmented reality, handheld camera
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.