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 201–300 of 1,004
Hybrid Indoor Localization Using IMU Sensors and Smartphone Camera
Poulose, A., & Han, D. S. (2019) · Sensors · doi:10.3390/s19235084 · Cited by 121
“The SLAM technique is classified as extended Kalman filter (EKF) SLAM [65,66], FastSLAM [67], low dimensionality (L)-SLAM [68], GraphSLAM [69], Occupancy Grid SLAM [70–72], distributed particle (DP)-SLAM [73], parallel tracking and mapping (PTAM) [74], stereo parallel tracking and mapping (S-PTAM) [75], dense tracking a…”
MethodDepth from motion for smartphone AR
Valentin, J., Kowdle, A., Barron, J. T., Wadhwa, N., Dzitsiuk, M., Schoenberg, M., Verma, V., Csaszar, A., Turner, E., Dryanovski, I., et al. (2018) · ACM Transactions on Graphics · doi:10.1145/3272127.3275041 · Cited by 132
“The approach described in [Ondrúška et al. 2015] generates sparse depth maps of size 320 × 240 at 50Hz on an iPhone GPU using an approximation of PatchMatch Stereo [Bleyer et al. 2011] and a dense tracking pipeline akin to DTAM [Newcombe et al. 2011] but with IMU initialization.”
MethodReal-Time RGB-D Camera Relocalization via Randomized Ferns for Keyframe Encoding
Glocker, B., Shotton, J., Criminisi, A., & Izadi, S. (2014) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2014.2360403 · Cited by 124
“We also evaluated the importance of using both color and depth information for the relocalization and compared the performance to two setups where we use either RGB or depth only.”
BackgroundInfluentialAutonomous Vision‐based Micro Air Vehicle for Indoor and Outdoor Navigation
Schmid, K., Lutz, P., Tomić, T., Mair, E., & Hirschmüller, H. (2014) · Journal of Field Robotics · doi:10.1002/rob.21506 · Cited by 108
“Modern approaches are often based on matching dense depth images (Newcombe, Lovegrove, and Davison, 2011b; Newcombe et al., 2011a; Sturm, Burgard, & Cremers, 2012), but they require high processing power and are often imple-mentedontheGPU.”
BackgroundSemantics for Robotic Mapping, Perception and Interaction: A Survey
Garg, S., Sünderhauf, N., Dayoub, F., Morrison, D., Cosgun, A., Carneiro, G., Wu, Q., Chin, T.-J., Reid, I., Gould, S., et al. (2020) · Foundations and Trends® in Robotics · doi:10.1561/2300000059 · Cited by 105
Lovegrove, S., Patron-Perez, A., & Sibley, G. (2013) · Procedings of the British Machine Vision Conference 2013 · doi:10.5244/c.27.93 · Cited by 106
“Each scanline is effectively a single push-broom camera (left); such scanline-camera measurements are captured over time, which defines the image returned by the actual sensor (right). sequences, such as [9] [18] [24] [28].”
BackgroundSelf-citationConvolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images
Ran, L., Zhang, Y., Zhang, Q., & Yang, T. (2017) · Sensors · doi:10.3390/s17061341 · Cited by 118
Yang, N., Wang, R., Gao, X., & Cremers, D. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2846813 · Cited by 137
“Direct methods use either all pixels (dense) [6], pixels with sufficiently large intensity gradient (semi-dense) [4], or sparsely selected pixels (sparse) [8] and minimize a photometric error obtained by direct image alignment on the used pixels, based on the brightness constancy assumption.”
MethodTowards autonomous mapping in agriculture: A review of supportive technologies for ground robotics
Fasiolo, D. T., Scalera, L., Maset, E., & Gasparetto, A. (2023) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2023.104514 · Cited by 140
Virtual and Augmented Reality on the 5G Highway
Orlosky, J., Kiyokawa, K., & Takemura, H. (2017) · Journal of Information Processing · doi:10.2197/ipsjjip.25.133 · Cited by 107
“Though many systems have realized dense 3D reconstructions through techniques like DTAM [39] or KinectFusion [40], the constant sharing and synchronization of these environments between users is still a significant challenge.”
BackgroundVisual SLAM for Automated Driving: Exploring the Applications of Deep Learning
Milz, S., Arbeiter, G., Witt, C., Abdallah, B., & Yogamani, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00062 · Cited by 107
Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry
Xue, F., Wang, X., Li, S., Wang, Q., Wang, J., & Zha, H. (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.2019.00877 · Cited by 127
DepthNet: A Recurrent Neural Network Architecture for Monocular Depth Prediction
Kumar, A. C. S., Bhandarkar, S. M., & Prasad, M. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00066 · Cited by 140
Accurate Dynamic SLAM Using CRF-Based Long-Term Consistency
Du, Z., Huang, S.-S., Mu, T., Zhao, Q., Martin, R. R., & Xu, K. (2020) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2020.3028218 · Cited by 116
“, DTAM [19], SVO [20], LSD-SLAM [21], InfiniTAM [22], PSM-SLAM [23] and DSO [24].”
Dense reconstruction on-the-fly
Wendel, A., Maurer, M., Graber, G., Pock, T., & Bischof, H. (2012) · 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.2012.6247833 · Cited by 121
“While powerful and accurate Structure–from–Motion pipelines [16, 15] have been available for several years, three major problems prohibited a wide-spread use of 3D reconstruction on mobile devices: First, many approaches are not suitable for devices with low computational capabilities.”
BackgroundA Spline-Based Trajectory Representation for Sensor Fusion and Rolling Shutter Cameras
Patron-Perez, A., Lovegrove, S., & Sibley, G. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0811-3 · Cited by 104
“A number of real-time visual odometry and SLAM systems have been proposed previously, including those that operate on stereo (Comport et al. 2007; Mei et al. 2010; Strasdat et al. 2011) and monocular sequences (Davison 2003; Klein and Murray 2008; Strasdat et al. 2010; Newcombe et al. 2011).”
BackgroundSelf-citationAn augmented reality application for improving shopping experience in large retail stores
Cruz, E., Orts‐Escolano, S., Gomez‐Donoso, F., Rizo-Maestre, C., Rangel, J. C., Mora, H., & Cazorla, M. (2018) · Virtual Reality · doi:10.1007/s10055-018-0338-3 · Cited by 126
“The mobile application was developed using an AR library (Kudan2) which provides us with markerless tracking of the scene (Klein and Murray 2009; Newcombe et al. 2011).”
MethodMilestones in Autonomous Driving and Intelligent Vehicles—Part II: Perception and Planning
Chen, L. F., Teng, S., Li, B., Na, X., Li, Y., Li, Z., Wang, J., Cao, D., Zheng, N., & Wang, F. (2023) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2023.3283021 · Cited by 123
3D Modeling on the Go: Interactive 3D Reconstruction of Large-Scale Scenes on Mobile Devices
Schöps, T., Sattler, T., Häne, C., & Pollefeys, M. (2015) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2015.40 · Cited by 114
DVL-SLAM: sparse depth enhanced direct visual-LiDAR SLAM
Shin, Y.-S., Park, Y. S., & Kim, A. (2019) · Autonomous Robots · doi:10.1007/s10514-019-09881-0 · Cited by 120
“Recently, direct methods have been introduced that directly use the intensity of the image (Forster et al. (2014); Engel et al. (2017); Newcombe et al. (2011b); Kerl et al. (2013b); Steinbrcker et al. (2011); Engel et al. (2014)).”
MethodInfluentialElastic Fragments for Dense Scene Reconstruction
Zhou, Q.-Y., Miller, S., & Koltun, V. (2013) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.65 · Cited by 114
“Substantial progress on dense scene reconstruction from photographs and video sequences has been made, despite the ambiguity of photometric cues [20, 26, 21, 6, 15, 17].”
BackgroundFörster, C., Faessler, M., Fontana, F., Werlberger, M., & Scaramuzza, D. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7138988 · Cited by 116
“Real-time dense reconstruction with a single camera has been previously demonstrated in [8], [9], [12]–[14].”
MethodPennCOSYVIO: A challenging Visual Inertial Odometry benchmark
Pfrommer, B., Sanket, N. J., Daniilidis, K., & Cleveland, J. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989443 · Cited by 118
“Pure visual odometry [10] [11] [12] [13] [14] has enjoyed considerable success, but at the moment, VIO based on the fusion of camera (to eliminate drift and establish loop closure) and IMU data (for rapid rotations) [15] [16] [17] appears to be the most promising approach.”
BackgroundCollaborative visual SLAM for multiple agents:A brief survey
Zou, D., Tan, P., & Yu, W. (2019) · Virtual Reality & Intelligent Hardware · doi:10.1016/j.vrih.2019.09.002 · Cited by 99
Mesh Based Semantic Modelling for Indoor and Outdoor Scenes
Valentin, J. P. C., Sengupta, S., Warrell, J., Shahrokni, A., & Torr, P. H. S. (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.2013.269 · Cited by 116
“The advent of inexpensive depth sensors has significantly encouraged developments in scene reconstruction using streams of depth and RGB data [18, 19].”
BackgroundMonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera
Wimbauer, F., Yang, N., von Stumberg, L., Zeller, N., & Cremers, D. (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/cvpr46437.2021.00605 · Cited by 128
“[36] instead jointly optimize the 6DoF camera pose and the dense 3D scene structure.”
MethodPhotometric Bundle Adjustment for Dense Multi-view 3D Modeling
Delaunoy, A., & Pollefeys, M. (2014) · 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.2014.193 · Cited by 97
Real-time navigation in 3D environments based on depth camera data
Maier, D., Hornung, A., & Bennewitz, M. (2012) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2012.6651595 · Cited by 97
“Recently, approaches have been presented that perform SLAM with RGB-D cameras [15, 16, 17].”
MethodVisual–Inertial Navigation Systems for Aerial Robotics: Sensor Fusion and Technology
Santoso, F., Garratt, M., & Anavatti, S. G. (2016) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2016.2582752 · Cited by 109
“Considering the use of optical flow in an MAV navigation system, it is also necessary to eliminate the effects of rotational movements of the aircraft and only consider the components generated by the translational motion in order to extract range information, resulting in noisy estimation of the…”
Deep Learning for Visual Localization and Mapping: A Survey
Chen, C., Wang, B., Lu, C. X., Trigoni, N., & Markham, A. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3309809 · Cited by 97
“In DeepTAM [244], the depth and pose predictions from DNNs are integrated into a classical DTAM system [177], where the system estimates small pose increments and accumulates information in a cost volume to update the depth prediction.”
InfluentialConcha, A., Loianno, G., Kumar, V., & Civera, J. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487266 · Cited by 108
“• Jacobian of the acceleration bias error r imu[5] with respect to the acceleration bias ba”
BackgroundInfluentialIllumination change robustness in direct visual SLAM
Park, S., Schöps, T., & Pollefeys, M. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989525 · Cited by 103
Improving monocular visual SLAM in dynamic environments: an optical-flow-based approach
Cheng, J., Sun, Y., & Meng, M. Q. ‐. (2019) · Advanced Robotics · doi:10.1080/01691864.2019.1610060 · Cited by 103
“Low cost, easy calibration and portability make the monocular camera a very popular sensor for visual SLAM [9–15].”
BackgroundEdge-SLAM: Edge-Assisted Visual Simultaneous Localization and Mapping
Ali, A. J. B., Kouroshli, M., Semenova, S., Hashemifar, Z. S., Ko, S. Y., & Dantu, K. (2022) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3561972 · Cited by 117
“Systems such as PTAM [37], DTAM [52], LSD-SLAM [21] used monocular cameras for SLAM.”
MethodUnsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency
Yang, Z., Wang, P., Xu, W. H., Zhao, L., & Nevatia, R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.03665 · Cited by 92
“One group of approaches solve this problem by feature matching and estimating camera and scene geometries, e.g.structure from motion (SFM) (Wu and others 2011) etc., or color matching, e.g.DTAM (Newcombe, Lovegrove, and Davison 2011).”
BackgroundMethodSimpleRecon: 3D Reconstruction Without 3D Convolutions
Sayed, M., Gibson, J., Watson, J., Prisacariu, V. A., Firman, M., & Godard, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19827-4_1 · Cited by 154
Continuous 3D Perception Model with Persistent State
Wang, Q., Zhang, Y., Holynski, A., Efros, A. A., & Kanazawa, A. (2025) · 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/cvpr52734.2025.00983 · Cited by 690
“…traditional methods such as Structure from Motion (SfM) [1, 2, 28, 47, 65, 66, 70, 71, 80] and Simultaneous Localization and Mapping (SLAM) [11, 16, 19, 22, 37, 51, 53], as well as more recent approaches such as Neural Radiance Fields (NeRF) [12, 24, 49, 50, 84] and 3D Gaussian Splatting [36].”
ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments
An, D., Wang, H., Wang, W., Wang, Z., Huang, Y., He, K., & Wang, L. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3386695 · Cited by 103
“Researchers have investigated explicit metric spatial representations [59], and examined the construction of these representations using various sensors [60], [61], as well as how to locate agents with such representations [62], [63].”
SurfelMeshing: Online Surfel-Based Mesh Reconstruction
Schöps, T., Sattler, T., & Pollefeys, M. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2947048 · Cited by 108
“This has led to dense Simultaneous Localization and Mapping (SLAM) systems [1], [2], online 3D scene perception approaches [3], [4], and applications such as Augmented Reality (AR) [5], [6] building on top of SLAM and densemapping.”
BackgroundAutonomous Navigation for eVTOL: Review and Future Perspectives
Wei, H., Lou, B., Zhang, Z., Liang, B., Wang, F., & Lv, C. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3352613 · Cited by 118
“Dense tracking and mapping, proposed by Newcombe et al. [66], exemplifies this approach, offering accurate mapping even under rapid motion but at the expense of higher computational requirements.”
BackgroundMASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
Murai, R., Dexheimer, E., & Davison, A. J. (2025) · 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/cvpr52734.2025.01556 · Cited by 354
“To improve robustness and provide interaction, early dense monocular SLAM systems demonstrated alternating optimisation of poses and dense depth with handcrafted regularisation [29].”
Self-citationTurning Mobile Phones into 3D Scanners
Kolev, K., Tanskanen, P., Speciale, P., & Pollefeys, M. (2014) · 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.2014.504 · Cited by 101
“Interactive systems based on video cameras [6] and depth sensors [14, 7] have been demonstrated.”
BackgroundBeyond Photometric Loss for Self-Supervised Ego-Motion Estimation
Shen, T., Luo, Z., Zhou, L., Deng, H., Zhang, R., Fang, T., & Quan, L. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793479 · Cited by 106
“Examples include [32], [7], [6].”
Survey on Localization Systems and Algorithms for Unmanned Systems
Yuan, S., Wang, H., & Xie, L. (2021) · Unmanned Systems · doi:10.1142/s230138502150014x · Cited by 100
Computer Vision Metrics: Survey, Taxonomy, and Analysis
Krig, S. (2014) · Apress eBooks · doi:10.1007/978-1-4302-5930-5 · Cited by 166
Fast depth densification for occlusion-aware augmented reality
Holynski, A., & Kopf, J. (2018) · ACM Transactions on Graphics · doi:10.1145/3272127.3275083 · Cited by 92
“Some SLAMmethods attempt to reconstruct a dense depth map that covers all pixels in the video [M. Pizzoli 2014; Newcombe et al. 2011].”
BackgroundKeyframe‐based thermal–inertial odometry
Khattak, S., Papachristos, C., & Alexis, K. (2019) · Journal of Field Robotics · doi:10.1002/rob.21932 · Cited by 101
“Direct visual odometry methods that rely on the minimization of photometric error, such as methods discussed in Newcombe, Lovegrove, and Davison (2011) and Pizzoli, Forster, and Scaramuzza (2014), typically require the optimization to be performed on a large number of points and thus become…”
MethodA review of visual SLAM for robotics: evolution, properties, and future applications
Al-Tawil, B., Hempel, T., Abdelrahman, A. A., & Al-Hamadi, A. K. (2024) · Frontiers in Robotics and AI · doi:10.3389/frobt.2024.1347985 · Cited by 126
“The DTAM-SLAM workflow is divided into a series of steps, each with its own purpose (Ne et al., 2011; Macario Barros et al., 2022).”
Loc-NeRF: Monte Carlo Localization using Neural Radiance Fields
Maggio, D., Abate, M., Shi, J., Mario, C., & Carlone, L. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160782 · Cited by 134
“In some works, instead of sparse keypoints, a dense representation is used to represent the 3D environment [42].”
BackgroundDai, A., Nießner, M., Zollhöfer, M., Izadi, S., & Theobalt, C. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1604.01093 · Cited by 88
An Indoor Wayfinding System Based on Geometric Features Aided Graph SLAM for the Visually Impaired
Zhang, H., & Ye, C. (2017) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2017.2682265 · Cited by 98
“Most recently, SLAM methods based on whole image alignment, instead of visual feature matching, are introduced for real-time camera tracking and reconstruction on GPU [20] and CPU [21].”
MethodPoint-Plane SLAM Using Supposed Planes for Indoor Environments
Zhang, X., Wang, W., Qi, X., Liao, Z., & Wei, R. (2019) · Sensors · doi:10.3390/s19173795 · Cited by 95
“Some other point-based SLAM methods can also obtain a sparse map [9], semi-dense map [10] or even dense map [11,12].”
MethodA review of visual inertial odometry from filtering and optimisation perspectives
Gui, J., Gu, D., Wang, S., & Hu, H. (2015) · Advanced Robotics · doi:10.1080/01691864.2015.1057616 · Cited by 110
“[15] In mapping stage, features, such as corners, edges or other landmarks in 3D space, are extracted from an image via various features detectors.”
BackgroundMethodInfluentialDirect, Dense, and Deformable: Template-Based Non-rigid 3D Reconstruction from RGB Video
Yu, R., Russell, C., Campbell, N. D. F., & Agapito, L. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.111 · Cited by 94
“While spectacular progress has been made in monocular dense 3D reconstruction of static scenes from video [19, 28, 13, 31], direct 3D capture of dense non-rigid shapes from a single video stream lies significantly behind.”
BackgroundUnsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery
Shamwell, E. J., Lindgren, K., Leung, S., & Nothwang, W. D. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2909895 · Cited by 86
“Monocular VO approaches recover translation up to an unknown scale [13], [14], [15], [16] as depth is unobservable from monocular cameras and thus there is ambiguity in the scale of translational estimates.”
Background4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving
Wenzel, P., Wang, R., Yang, N., Cheng, Q., Khan, Q., von Stumberg, L., Zeller, N., & Cremers, D. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-71278-5_29 · Cited by 113
“During the last decade, research on visual odometry (VO) and simultaneous localization and mapping (SLAM) has made tremendous strides [30,12,29,11] particularly in the context of autonomous driving (AD) [9,44,46,28].”
BackgroundE-NeRF: Neural Radiance Fields From a Moving Event Camera
Klenk, S., Koestler, L., Scaramuzza, D., & Cremers, D. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3240646 · Cited by 92
“led by methods that produce sparse point clouds [31], [32], depth maps [30] or voxel grids [33].”
MethodThe History of Mobile Augmented RealityPreprint
Arth, C., Grasset, R., Gruber, L., Langlotz, T., Mulloni, A., & Wägner, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.01319 · Cited by 159
“At ICCV 2011, Newcombe presents DTAM, a dense real-time tracking and mapping algorithm [47].”
Real-Time Monocular Object-Model Aware Sparse SLAM
Hosseinzadeh, M., Li, K., Latif, Y., & Reid, I. D. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793728 · Cited by 93
“Denser representations [2], [3], [4], [5], [6], remain equivalent to a collection of points in this regard.”
BackgroundRegularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
Wang, K., Zhang, Z., Yan, Z., Li, X., Xu, B., Li, J., & Yang, J. J. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01575 · Cited by 125
“Monocular depth estimation is a fundamental topic in computer vision as it has wide range of applications in augmented reality [35], robotics [11] and autonomous driving [34], etc .”
SemanticPaint: Interactive 3D Labeling and Learning at your Fingertips
Valentin, J., Vineet, V., Cheng, M., Kim, D., Shotton, J., Kohli, P., Nießner, M., Criminisi, A., Izadi, S., & Torr, P. H. S. (2015) · ACM Transactions on Graphics · doi:10.1145/2751556 · Cited by 116
“We adopt the truncated signed distance function (TSDF) of Curless and Levoy [1996] to fuse depth images into a 3D volume as in KinectFusion [Newcombe et al. 2011a; Izadi et al. 2011].”
MethodCollision Avoidance for Quadrotors with a Monocular Camera
Alvarez, H., Paz, L. M., Sturm, J., & Cremers, D. (2015) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-23778-7_14 · Cited by 88
“Analogous to DTAM [11], we follow a multi-view stereo approach based on energy minimization that consists of two stages: The first stage involves the calculation of a cost volume that accumulates the photo-consistency errors of the overlapping images for different inverse depths.”
BackgroundMethodInfluentialDirect Visual Odometry in Low Light Using Binary Descriptors
Alismail, H., Kaess, M., Browning, B., & Lucey, S. (2016) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2016.2635686 · Cited by 88
“Simpler descriptors, such as photometrically normalized image patches [22] or the gradientconstraint [39] are efficient to compute, but do not possess sufficient invariance to radiometric changes in the wild.”
BackgroundSimultaneous Localization and Mapping in the Epoch of Semantics: A Survey
Sualeh, M., & Kim, G.-W. (2018) · International Journal of Control Automation and Systems · doi:10.1007/s12555-018-0130-x · Cited by 94
“DTAM [121] 11 Mo D Gradient BA COCOLIB - + + - + GPSLAM [122] 11 R F SIFT PG G2O - - + + + -”
Algorithms for 3D Shape Scanning with a Depth Camera
Cui, Y., Schuon, S., Thrun, S., Stricker, D., & Theobalt, C. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.190 · Cited by 95
“And recently they presented an approach that allows camera tracking even under sparse texture scene by matching dense depth maps [34].”
BackgroundA real-time method for depth enhanced visual odometry
Zhang, J., Kaess, M., & Singh, S. (2015) · Autonomous Robots · doi:10.1007/s10514-015-9525-1 · Cited by 91
“With a single camera (Klein and Murray 2007; Newcombe et al. 2011; Engel et al. 2013; Forster et al. 2014), if assuming unconstrained motion, rotation can be recovered but translation is up to scale.”
BackgroundKeyframe-based Direct Thermal–Inertial Odometry
Khattak, S., Papachristos, C., & Alexis, K. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793927 · Cited by 81
“Historically, direct visual odometry methods based on the minimization of photometric error such as [20–22], require optimization to be performed on a large number of points and thus becoming computationally expensive.”
Air-ground localization and map augmentation using monocular dense reconstruction
Förster, C., Pizzoli, M., & Scaramuzza, D. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696924 · Cited by 84
“Computing a dense 3D surface from monocular cameras in real-time has only recently become feasible with the use of GPGPU computing [3], [4].”
BackgroundInfluentialMap2DFusion: Real-time incremental UAV image mosaicing based on monocular SLAM
Bu, S., Zhao, Y., Wan, G., & Liu, Z. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759672 · Cited by 107
“As most methods detect keypoint features for matching, Newcombe et al. propose a direct approach named DTAM [16] where camera motion is computed by minimizing a global spatially regularized energy function on GPU.”
BackgroundInfluentialWu, P.-C., Wang, R. Y., Kin, K., Twigg, C. D., Han, S., Yang, M., & Chien, S. (2017) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3126594.3126664 · Cited by 81
DM-SLAM: A Feature-Based SLAM System for Rigid Dynamic Scenes
Cheng, J., Wang, Z., Zhou, H., Li, L., & Yao, J. (2020) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi9040202 · Cited by 86
“Many visual SLAM systems have achieved excellent performance under certain circumstances (e.g., DTAM [1], LSD-SLAM [2], and ORB-SLAM2 [3]).”
MethodDeep Learning Techniques for Visual SLAM: A Survey
Mokssit, S., Licea, D. B., Guermah, B., & Ghogho, M. (2023) · IEEE Access · doi:10.1109/access.2023.3249661 · Cited by 93
“Classical VSLAM techniques can be divided into two categories: feature-based approaches [15], [16], [35] and dense approaches [36], [37], [38].”
PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment
Deng, T., Shen, G., Qin, T., Wang, J., Zhao, W., Wang, J., Wang, D., & Chen, W. (2024) · 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/cvpr52733.2024.01859 · Cited by 94
“They can estimate the camera pose and construct sparse point cloud maps in real-time with accurate localization performance.”
BackgroundOmnidirectional CNN for Visual Place Recognition and Navigation
Wang, T.-H. J., Huang, H.-J., Lin, J.-T., Hu, C.-W., Zeng, K.-H., & Sun, M. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8463173 · Cited by 92
Realtime Edge-Based Visual Odometry for a Monocular Camera
Tarrio, J., & Pedre, S. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.87 · Cited by 88
“Even though some of these algorithms are able to run in real time in modern cpu+gpu equipment [19] [18] their computational cost is still too high for embedded solutions, in which the processing power is limited by weight (in the case of light aerial vehicles), power consumption or simply by commercial price when thin…”
BackgroundUser-Specific Hand Modeling from Monocular Depth Sequences
Taylor, J., Stebbing, R. V., Ramakrishna, V., Keskin, C., Shotton, J., Izadi, S., Hertzmann, A., & Fitzgibbon, A. W. (2014) · 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.2014.88 · Cited by 92
Patch‐Collaborative Spectral Point‐Cloud Denoising
Rosman, G., Dubrovina, A., & Kimmel, R. (2013) · Computer Graphics Forum · doi:10.1111/cgf.12139 · Cited by 79
Robust 3D Object Tracking from Monocular Images Using Stable Parts
Crivellaro, A., Rad, M., Verdié, Y., Yi, K. M., Fua, P., & Lepetit, V. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2708711 · Cited by 82
“Localization and Mapping (SLAM) [39], [40], [41].”
Semantic Monocular SLAM for Highly Dynamic Environments
Brasch, N., Božič, A., Lallemand, J., & Tombari, F. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593828 · Cited by 95
“Differently, direct methods [6], [2], [4], [3] minimize the photometric error based on the projection of the pixel intensities from one image into the other.”
BackgroundLin, B., Sun, Y., Qian, X., Goldgof, D. B., Gitlin, R. D., & You, Y. (2015) · International Journal of Medical Robotics and Computer Assisted Surgery · doi:10.1002/rcs.1661 · Cited by 87
“The dense model from (123) was later used to improve the camera tracking in (128).”
MethodSimultaneous Localization And Mapping: Present, Future, and the Robust-Perception Age.Preprint
Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I. D., & Leonard, J. J. (2016) · arXiv (Cornell University) · Cited by 90
SLAM Overview: From Single Sensor to Heterogeneous Fusion
Chen, W., Zhou, C., Shang, G., Wang, X., Li, Z., Xu, C., & Hu, K. (2022) · Remote Sensing · doi:10.3390/rs14236033 · Cited by 91
Experimental Comparison of Open Source Vision-Based State Estimation Algorithms
Li, A. Q., Coskun, A., Doherty, S. M., Ghasemlou, S., Jagtap, A., Modasshir, M., Rahman, S., Singh, A. K., Xanthidis, M., O’Kane, J. M., et al. (2017) · Springer proceedings in advanced robotics · doi:10.1007/978-3-319-50115-4_67 · Cited by 82
“Ongoing work includes the study of the effects of changing parameters, collection of data focusing on different type of motions, and the investigation of more open-source packages on the same datasets, including DTAM [27], DPPTAM [6], OKVis [23].”
BackgroundMahajan, H. B., Uke, N., Pise, P. D., Shahade, M., Dixit, V. G., Bhavsar, S., & Deshpande, S. D. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-14253-5 · Cited by 87
“Various systems, such as MonoSLAM [66], Parallel Tracking And Mapping (PTAM) [28], Fusion Algorithm Based Mapping (FAB-MAP) [16], Dense Tracking And Mapping (DTAM) [52], and KinectFusion [53], have been introduced.”
BackgroundMethodComparison of ROS-based visual SLAM methods in homogeneous indoor environment
Ibragimov, I. Z., & Afanasyev, I. M. (2017) · Workshop on Positioning, Navigation and Communications (WPNC) · doi:10.1109/wpnc.2017.8250081 · Cited by 83
“Since the earliest real-time methods like MonoSLAM [2] and Parallel Tracking and Mapping (PTAM, [7]), the number of monocular SLAM-related methods has grown with appearance of Dense Tracking and Mapping (DTAM, [10]), Large-Scale Direct Monocular SLAM (LSD-SLAM, [3]), Oriented FAST and Rotated BRIEF (ORB-SLAM, [9]), De…”
MethodCarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles
Reddy, N. D., Vo, M., & Narasimhan, S. G. (2018) · 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.2018.00204 · Cited by 100
Robust Object-based SLAM for High-speed Autonomous Navigation
Ok, K., Liu, K., Frey, K. M., How, J. P., & Roy, N. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794344 · Cited by 85
“Dense methods [6], [7] address the problem of sparsity by using a volumetric or mesh-based representation, but these methods often have a high computational burden, while the reconstruction quality deteriorates in scenes with low texture.”
MethodDynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction
Chen, C., Lu, C. X., Wang, B., Trigoni, N., & Markham, A. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3112460 · Cited by 85
Auto-Rectify Network for Unsupervised Indoor Depth Estimation
Bian, J.-W., Zhan, H., Wang, N., Chin, T.-J., Shen, C., & Reid, I. D. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3136220 · Cited by 127
“Depending on the specific use case, it is usually solved by Structure-fromMotion [1] or Visual SLAM [2], [3], [4].”
MethodCreating the Future: Augmented Reality, the next Human-Machine Interface
Abrash, M. (2021) · Technical digest - International Electron Devices Meeting/Technical digest · doi:10.1109/iedm19574.2021.9720526 · Cited by 75
RNNSLAM: Reconstructing the 3D colon to visualize missing regions during a colonoscopy
Ma, R., Wang, R., Zhang, Y., Pizer, S. M., McGill, S., Rosenman, J. G., & Frahm, J. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102100 · Cited by 99
CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-Aware 3D Gaussian Field
Hu, J., Chen, X., Feng, B., Li, G., Yang, L., Bao, H., Zhang, G., & Cui, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72698-9_6 · Cited by 144
Hierarchical Voxel Block Hashing for Efficient Integration of Depth Images
Kähler, O., Prisacariu, V. A., Valentin, J., & Murray, D. W. (2015) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2015.2512958 · Cited by 77
“Kinect-Fusion [1], [2], which uses RGB-D imagery as input, is a widely acclaimed exemplar, whereas others methods, e.g. [3], [4] compute dense geometric data from visual imagery alone.”
MethodOngoing Evolution of Visual SLAM from Geometry to Deep Learning: Challenges and Opportunities
Li, R., Wang, S., & Gu, D. (2018) · Cognitive Computation · doi:10.1007/s12559-018-9591-8 · Cited by 85
“proposed a dense tracking and mapping (DTAM) system [4].”
SemanticPaint: Interactive 3D Labeling and Learning at your FingertipsPreprint
Valentin, J., Vineet, V., Cheng, M., Kim, D., Shotton, J., Kohli, P., Nießner, M., Criminisi, A., Izadi, S., & Torr, P. H. S. (2015) · arXiv (Cornell University) · Cited by 74
Geometric Loss Functions for Camera Pose Regression with Deep Learning
Kendall, A., & Cipolla, R. (2017) · arXiv (Cornell University) · doi:10.17863/cam.26496 · Cited by 73
A Novel Representation of Parts for Accurate 3D Object Detection and Tracking in Monocular Images
Crivellaro, A., Rad, M., Verdié, Y., Yi, K. M., Fua, P., & Lepetit, V. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.499 · Cited by 80
“Finally, a very active and related field is SLAM (Simultaneous Localization and Mapping) [15] [24] [6].”
BackgroundMonocular Depth Prediction Using Generative Adversarial Networks
Kumar, A. C. S., Bhandarkar, S. M., & Prasad, M. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00068 · Cited by 84
Aerial orthoimage generation for UAV remote sensing: Review
Zhang, J., Xu, S., Zhao, Y., Sun, J., Xu, S., & Zhang, X. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.08.007 · Cited by 88
A hand-held AR magic lens with user-perspective rendering
Baričević, D., Lee, C., Turk, M., Höllerer, T., & Bowman, D. A. (2012) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2012.6402557 · Cited by 75
“These devices also provide back-facing cameras and sensors which can be used to track the device with respect to the world via computer vision techniques [31, 13, 20].”
Background
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.