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 101–200 of 1,004
Large-scale direct SLAM for omnidirectional cameras
Caruso, D., Engel, J., & Cremers, D. (2015) · 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353366 · Cited by 244
“More recently, so-called direct approaches have gained in popularity: instead of abstracting the images to pointobservations , the idea is to compute dense [9], or semidense [10] depth maps in an incremental fashion, and track the camera using direct image alignment.”
BackgroundNeural Topological SLAM for Visual Navigation
Singh Chaplot, D., Salakhutdinov, R., Gupta, A., & Gupta, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01289 · Cited by 241
Event-Based Stereo Visual Odometry
Zhou, Y., Gallego, G., & Shen, S. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3062252 · Cited by 240
“However, we contribute some fundamental differences guided by a real-time design goal: (i) The objective function is built only on the temporal inconsistency across one stereo event time-surface map (Section IV-A) rather than over longer time spans (thus, the proposed approach becomes closer to the strategy in [52] th…”
BackgroundVox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representation
Yang, X., Li, H., Zhai, H., Ming, Y., Liu, Y., & Zhang, G. (2022) · 2022 IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar55827.2022.00066 · Cited by 234
“These poses are then coupled with their corresponding input point clouds to update a global map represented by geometric primitives such as cost volumes [20, 37], surfels [29, 35, 38] or voxels [12, 19, 21].”
BackgroundMethodInfluentialAutonomous aerial navigation using monocular visual‐inertial fusion
Lin, Y., Gao, F., Qin, T., Gao, W., Liu, T., Wu, W., Yang, Z., & Shen, S. (2018) · Journal of Field Robotics · doi:10.1002/rob.21732 · Cited by 237
End-to-end, sequence-to-sequence probabilistic visual odometry through deep neural networks
Wang, S., Clark, R., Wen, H., & Trigoni, N. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364917734298 · Cited by 238
“Dense tracking and mapping (DTAM) demonstrates real-time dense monocular SLAM (Newcombe et al., 2011).”
BackgroundTightly-coupled monocular visual-inertial fusion for autonomous flight of rotorcraft MAVs
Shen, S., Michael, N., & Kumar, V. (2015) · 2015 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2015.7139939 · Cited by 223
“Conditioning is also a popular method among the computer vision community to achieve constant computation complexity [13, 14].”
MethodDeepTAM: Deep Tracking and Mapping
Zhou, H., Ummenhofer, B., & Brox, T. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01270-0_50 · Cited by 226
Direct visual-inertial odometry with stereo cameras
Usenko, V., Engel, J., Stuckler, J., & Cremers, D. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487335 · Cited by 219
“More recently, direct methods have become popular also in a monocular environment, prominent examples include DTAM [26], SVO [10] and LSD-SLAM [4].”
BackgroundStaticFusion: Background Reconstruction for Dense RGB-D SLAM in Dynamic Environments
Scona, R., Jaimez, M., Petillot, Y. R., Fallon, M., & Cremers, D. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8460681 · Cited by 212
“In DTAM [11], which is a monocular dense mapping system, the authors discard pixels with a photometric error higher than a specific threshold.”
BackgroundMeaningful maps – Object-oriented semantic mapping
Sünderhauf, N., Pham, T. T., Latif, Y., Milford, M. J., & Reid, I. D. (2017) · QUT ePrints (Queensland University of Technology) · Cited by 227
Detailed Human Avatars from Monocular Video
Alldieck, T., Magnor, M., Xu, W., Theobalt, C., & Pons-Moll, G. (2018) · 2018 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2018.00022 · Cited by 206
Dense Variational Reconstruction of Non-rigid Surfaces from Monocular Video
Garg, R., Roussos, A., & Agapito, L. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.168 · Cited by 210
ROSEFusion: Random Optimization for Online Dense Reconstruction under Fast Camera Motion
Zhang, J., Zhu, C., Zheng, L., & Xu, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.05600 · Cited by 217
Learning Monocular Depth by Distilling Cross-Domain Stereo Networks
Guo, X., Li, H., Yi, S., Ren, J., & Wang, X. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01252-6_30 · Cited by 208
Point-plane SLAM for hand-held 3D sensors
Taguchi, Y., Jian, Y.-D., Ramalingam, S., & Feng, C. (2013) · 2013 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2013.6631318 · Cited by 214
“Although there has been several impressive results for real-time sparse [1] and dense [2], [3] 3D reconstruction using a hand-held 2D camera, several challenges such as reconstruction of textureless regions continue to persist.”
BackgroundEvent-Based, 6-DOF Camera Tracking from Photometric Depth Maps
Gallego, G., Lund, J. E. A., Mueggler, E., Rebecq, H., Delbruck, T., & Scaramuzza, D. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2769655 · Cited by 211
“These can be obtained from a previous mapping stage by means of classical dense reconstruction approaches using standard cameras (e.g., DTAM [16] or REMODE [17]) or even using a DVS (future research).”
BackgroundAn Overview on Visual SLAM: From Tradition to Semantic
Chen, W., Shang, G., Ji, A., Zhou, C., Wang, X., Xu, C., Li, Z., & Hu, K. (2022) · Remote Sensing · doi:10.3390/rs14133010 · Cited by 211
Multi-resolution surfel maps for efficient dense 3D modeling and tracking
Stückler, J., & Behnke, S. (2014) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2013.02.008 · Cited by 209
Comparison of Various SLAM Systems for Mobile Robot in an Indoor Environment
Filipenko, M., & Afanasyev, I. (2018) · 2018 International Conference on Intelligent Systems (IS) · doi:10.1109/is.2018.8710464 · Cited by 199
“Over the past decade, numerous methods have been proposed, including Parallel Tracking and Mapping (PTAM, [17], [18]), REgularized MOnocular Depth Estimation (REMODE, [19]), Oriented FAST [20] and Rotated BRIEF [21] (ORB-SLAM, [22], [23]), Dense Tracking and Mapping in Real-Time (DTAM, [24]), Large-Scale Direct monocu…”
Exploring Representation Learning With CNNs for Frame-to-Frame Ego-Motion Estimation
Costante, G., Mancini, M., Valigi, P., & Ciarfuglia, T. A. (2016) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2015.2505717 · Cited by 203
“Clearly, dense methods can achieve better accuracy than feature-based ones, but are more computationally intense, and only recently some have reached real-time operation on common hand-held devices or embedded systems, enabling their use on Micro Aerial Vehicle (MAV) platforms [2], [3], [4].”
BackgroundMethodRecurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth
Wang, R., Pizer, S. M., & Frahm, J.-M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00570 · Cited by 198
“SfM is typically used for offline 3D reconstruction from unordered image collections, while visual SLAM aims for a real-time solution using a single camera [3, 26].”
MethodReal-time RGB-D camera relocalization
Glocker, B., Izadi, S., Shotton, J., & Criminisi, A. (2013) · 2013 IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2013.6671777 · Cited by 195
“Recent advances in dense tracking and mapping [14] have enabled systems for accurate, real-time 3D reconstruction of the physical world using low cost commodity hardware [13] such as Microsoft’s Kinect sensor.”
BackgroundVisual Odometry Revisited: What Should Be Learnt?
Zhan, H., Weerasekera, C. S., Bian, J.-W., & Reid, I. (2020) · 2020 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra40945.2020.9197374 · Cited by 201
“Two dominant methods for geometry based VO/SLAM are feature-based [16]–[18] and direct methods [19], [20].”
MethodScalable 6-DOF Localization on Mobile Devices
Middelberg, S., Sattler, T., Untzelmann, O., & Kobbelt, L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10605-2_18 · Cited by 200
“In contrast to SLAM and PTAM, which construct sparse maps from features found in images, dense tracking and mapping (DTAM) builds a dense 3D model by estimating depth maps [25].”
BackgroundLive Metric 3D Reconstruction on Mobile Phones
Tanskanen, P., Kolev, K., Meier, L., Camposeco, F., Saurer, O., & Pollefeys, M. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.15 · Cited by 201
“Impressive results were obtained with video cameras [7] and depth sensors [15, 8].”
BackgroundMethodIncremental dense semantic stereo fusion for large-scale semantic scene reconstruction
Vineet, V., Miksik, O., Lidegaard, M., Niebner, M., Golodetz, S., Prisacariu, V. A., Kahler, O., Murray, D. W., Izadi, S., Peerez, P., et al. (2015) · 2015 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2015.7138983 · Cited by 200
“Early real-time dense approaches [18], [19] were able to estimate depth from monocular input, but their use of a regular voxel grid limited reconstruction to small volumes due to memory requirements.”
BackgroundMethodLEGO: Learning Edge with Geometry all at Once by Watching Videos
Yang, Z., Wang, P., Wang, Y., Xu, W., & Nevatia, R. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00031 · Cited by 192
Robotic weed control using automated weed and crop classification
Wu, X., Aravecchia, S., Lottes, P., Stachniss, C., & Pradalier, C. (2020) · Journal of Field Robotics · doi:10.1002/rob.21938 · Cited by 196
“(Pannacci et al., 2017). Tillett, Hague, and Miles (2002) mounted automatically guided hoes on the rear of the tractor to perform the interrow weeding at high speed, relying on real‐time crop row detection.”
BackgroundMethodInfluentialS-PTAM: Stereo Parallel Tracking and Mapping
Pire, T., Fischer, T., Castro, G., De Cristóforis, P., Civera, J., & Jacobo Berlles, J. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.03.019 · Cited by 192
“Other works using a monocular camera have produced fully dense and accurate maps with a TV-regularization of the photometric solution [46] or the addition of scene priors and learned patterns [47].”
Background3D Object Reconstruction from a Single Depth View with Adversarial Learning
Yang, B., Wen, H., Wang, S., Clark, R., Markham, A., & Trigoni, N. (2017) · 2017 IEEE International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw.2017.86 · Cited by 193
Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation
Yan, J., Zhao, H., Bu, P., & Jin, Y. (2021) · 2021 International Conference on 3D Vision (3DV) · doi:10.1109/3dv53792.2021.00056 · Cited by 173
DeepFactors: Real-Time Probabilistic Dense Monocular SLAM
Czarnowski, J., Laidlow, T., Clark, R., & Davison, A. J. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2965415 · Cited by 169
“This has spawned a new set of methods that use all image pixels and estimate a dense and more useful reconstruction of the observed scenes [7].”
Self-citationSalas-Moreno, R. F., Glocken, B., Kelly, P. H. J., & Davison, A. J. (2014) · 2014 IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2014.6948422 · Cited by 175
“These are extracted and refined over time to form a real-time dense planar SLAM system using depth images such as those produced by RGB-D sensors or via dense multi-view stereo reconstruction methods [18].”
MethodSelf-citationEnd-to-End Weakly-Supervised Semantic Alignment
Rocco, I., Arandjelovic, R., & Sivic, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00723 · Cited by 173
Recasens, D., Lamarca, J., Facil, J. M., Montiel, J. M. M., & Civera, J. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3095528 · Cited by 175
Roth, H., & Vona, M. (2012) · Procedings of the British Machine Vision Conference 2012 · doi:10.5244/c.26.112 · Cited by 172
“Beyond KinectFusion, Klein and Murray's parallel tracking and mapping (PTAM) system [12], and the more recent dense tracking and mapping (DTAM) reported by Newcombe et al [14], are both impressive.”
BackgroundDM-VIO: Delayed Marginalization Visual-Inertial Odometry
Stumberg, L. V., & Cremers, D. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3140129 · Cited by 171
“More recently, direct methods have been proposed, which optimize a photometric error function and can operate on dense [14] [15], semi-dense [16], or sparse point clouds [17].”
MethodDepth from focus with your mobile phone
Suwajanakorn, S., Hernandez, C., & Seitz, S. M. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298972 · Cited by 162
“Similar to [20], we perform a single Newton step around the minimum point to achieve sub-sample accuracy.”
MethodPM-Huber: PatchMatch with Huber Regularization for Stereo Matching
Heise, P., Klose, S., Jensen, B., & Knoll, A. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.293 · Cited by 166
“Our main contribution is an explicit variational smoothness model for the PatchMatch algorithm using quadratic relaxation [12, 17].”
MethodBenefit of large field-of-view cameras for visual odometry
Zhang, Z., Rebecq, H., Förster, C., & Scaramuzza, D. (2016) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2016.7487210 · Cited by 205
“Instead, it uses a direct method to estimate the camera motion by mimizing the photometric error of corresponding pixels in subsequent views, similar to LSD [19] and DTAM [20].”
MethodRobust Consistent Video Depth Estimation
Kopf, J., Rong, X., & Huang, J.-B. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00166 · Cited by 167
Zhang, J., Yang, X., Wang, W., Guan, J., Ding, L., & Lee, V. C. S. (2023) · Automation in Construction · doi:10.1016/j.autcon.2022.104699 · Cited by 165
Klingensmith, M., Dryanovski, I., Srinivasa, S., & Xiao, J. (2015) · Robotics: Science and Systems XI · doi:10.15607/rss.2015.xi.040 · Cited by 163
“Because mobile phones typically do not have depth sensors, previous works [9] [21] [22] on dense reconstruction for mobile phones have gone to great lengths to extract depth from a series of registered monocular camera images.”
BackgroundLarge-Scale Multi-resolution Surface Reconstruction from RGB-D Sequences
Steinbrucker, F., Kerl, C., & Cremers, D. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.405 · Cited by 158
Semi-dense visual odometry for AR on a smartphone
Schops, T., Engel, J., & Cremers, D. (2014) · 2014 IEEE International Symposium on Mixed and Augmented Reality (ISMAR) · doi:10.1109/ismar.2014.6948420 · Cited by 158
Unsupervised Learning of Geometry From Videos With Edge-Aware Depth-Normal Consistency
Yang, Z., Wang, P., Xu, W., Zhao, L., & Nevatia, R. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12257 · Cited by 156
Learning to Navigate the Energy Landscape
Valentin, J., Dai, A., Niessner, M., Kohli, P., Torr, P., Izadi, S., & Keskin, C. (2016) · 2016 Fourth International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2016.41 · Cited by 148
“To do so, we follow [31, 11] and minimize the photo-consistency error.”
BackgroundNICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM
Zhu, Z., Peng, S., Larsson, V., Cui, Z., Oswald, M. R., Geiger, A., & Pollefeys, M. (2024) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv62453.2024.00096 · Cited by 294
“Many dense visual SLAM methods have been introduced in the past years [34, 47, 62, 63, 35] and they are able to produce dense reconstructions of indoor scenes in real-time.”
BackgroundExploiting uncertainty in regression forests for accurate camera relocalization
Valentin, J., Niebner, M., Shotton, J., Fitzgibbon, A., Izadi, S., & Torr, P. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299069 · Cited by 156
“Simultaneous Localization and Mapping (SLAM) systems such as [14] [15] [17] [7] and commercial systems such as HoloLens or Project Tango demonstrate that visual SLAM is a maturing technology.”
BackgroundKeyframe-based monocular SLAM: design, survey, and future directions
Younes, G., Asmar, D., Shammas, E., & Zelek, J. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.09.010 · Cited by 191
“Similar to the work of Newcombe(Newcombe et al, 2011), Pretto et al (2011) modeled the environment as a 3D – Modeled the environment as a 3D piecewise smooth surface.”
MethodResultInfluentialRobust Dynamic Radiance Fields
Liu, Y.-L., Gao, C., Meuleman, A., Tseng, H.-Y., Saraf, A., Kim, C., Chuang, Y., Kopf, J., & Huang, J. (2023) · 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/cvpr52729.2023.00010 · Cited by 326
“From a collection of images, visual odometry estimates the 3D camera poses [18,19,46–48].”
BackgroundCritical Design and Control Issues of Indoor Autonomous Mobile Robots: A Review
Niloy, M. A., Shama, A., Chakrabortty, R. K., Ryan, M. J., Badal, F. R., Tasneem, Z., Ahamed, M. H., Moyeen, S. I., Das, S. K., Ali, M. F., et al. (2021) · IEEE Access · doi:10.1109/access.2021.3062557 · Cited by 189
“Some recent examples would be CNN-SLAM [314] which works on the back-end of LSD-SLAM [87], DeepTAM [315] which feeds both pose and depth information extracted through a DNN to a classical system DTAM [172].”
MethodVisual and Visual‐Inertial SLAM: State of the Art, Classification, and Experimental Benchmarking
Servières, M., Renaudin, V., Dupuis, A., & Antigny, N. (2021) · Journal of Sensors · doi:10.1155/2021/2054828 · Cited by 181
“The fi rst important direct method is the Dense Tracking and Mapping (DTAM) [34] from 2011.”
Almalıoğlu, Y., Saputra, M. R. U., de Gusmão, P. P. B., Markham, A., & Trigoni, N. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793512 · Cited by 197
“ronments with low texture, complex scene structure, and occlusions [19]–[22].”
BackgroundPerception and Navigation in Autonomous Systems in the Era of Learning: A Survey
Tang, Y. S., Zhao, C., Wang, J., Zhang, C., Sun, Q., Zheng, W. X., Du, W., Qian, F., & Kurths, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3167688 · Cited by 199
“…and understanding of the surrounding environment are indispensable for autonomous systems. vSLAM algorithms have been widely applied to model the environments into different types based on the actual requirements, including sparse map [16], semi-dense map [17], and dense map [18], as shown in Fig.”
BackgroundMethodA Photometrically Calibrated Benchmark For Monocular Visual OdometryPreprint
Engel, J. J., Usenko, V., & Cremers, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.02555 · Cited by 209
“…cameras (which often do not allow to either read or set parameters like the exposure time), we argue that for the above-mentioned use cases, this ultimately is the wrong approach: sensors – including cameras – can, and will be designed to fit the needs of the algorithms processing their data.”
BackgroundLianos, K.-N., Schönberger, J. L., Pollefeys, M., & Sattler, T. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01225-0_15 · Cited by 157
Real-time depth enhanced monocular odometry
Zhang, J., Kaess, M., & Singh, S. (2014) · 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2014.6943269 · Cited by 145
Behl, A., Jafari, O. H., Mustikovela, S. K., Alhaija, H. A., Rother, C., & Geiger, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.281 · Cited by 145
“This observation is in accordance with recent works on direct visual odometry and SLAM [7, 8, 27] which use similar measures to reliably estimate the camera pose in weakly textured environments.”
ResultSemi-dense 3D Reconstruction with a Stereo Event Camera
Zhou, Y., Gallego, G., Rebecq, H., Kneip, L., Li, H., & Scaramuzza, D. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01246-5_15 · Cited by 144
“Our method is inspired by multi-view stereo pipelines for conventional cameras, such as DTAM [30], which aim at maximizing the photometric consistency through a number of narrow-baseline video frames.”
MethodLightweight Unsupervised Deep Loop Closure
Merrill, N., & Huang, G. P. (2018) · Robotics: Science and Systems · doi:10.15607/rss.2018.xiv.032 · Cited by 171
DPPTAM: Dense piecewise planar tracking and mapping from a monocular sequence
Concha, A., & Civera, J. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7354184 · Cited by 157
“[7], [15] where the first ones presenting dense results in real-time using a monocular camera.”
BackgroundMethodLive Tracking and Dense Reconstruction for Handheld Monocular Endoscopy
Mahmoud, N., Collins, T., Hostettler, A., Soler, L., Doignon, C., & Montiel, J. M. M. (2018) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2856109 · Cited by 164
“differences (SSD) or sum of absolute difference (SAD) used by previous dense SLAM methods [6], [7].”
BackgroundMethodInfluentialReal-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations
Nekrasov, V., Dharmasiri, T., Spek, A., Drummond, T., Shen, C., & Reid, I. (2019) · 2019 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2019.8794220 · Cited by 138
“Traditionally, image based depth reconstruction was performed using SLAM based approaches [23]–[25].”
MethodUrban 3D semantic modelling using stereo vision
Sengupta, S., Greveson, E., Shahrokni, A., & Torr, P. H. S. (2013) · 2013 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2013.6630632 · Cited by 142
“[16] proposed a system for dense 3D reconstruction using a hand-held camera.”
BackgroundMethodInfluentialReal-Time Camera Tracking: When is High Frame-Rate Best?
Handa, A., Newcombe, R. A., Angeli, A., & Davison, A. J. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33786-4_17 · Cited by 159
“Known scene geometry enables the dense tracking component of the DTAM [3] system for dense monocular SLAM to used as as the tracker within our experiments, a pyramidal, GPGPU implementation of the whole image alignment method explained in Section 1.2.”
BackgroundMethodInfluentialSelf-citationVirtual-Blind-Road Following-Based Wearable Navigation Device for Blind People
Bai, J., Lian, S., Liu, Z., Wang, K., & Liu, D. (2018) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2018.2812498 · Cited by 155
PL-SVO: Semi-direct Monocular Visual Odometry by combining points and line segments
Gomez-Ojeda, R., Briales, J., & González-Jiménez, J. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759620 · Cited by 154
“In [20] authors propose a direct approach, known as DTAM, where they estimate the camera pose by direct alignment of the complete intensity image between each keyframe, employing a dense depth-map estimation.”
BackgroundIntegrating the physical environment into mobile remote collaboration
Gauglitz, S., Lee, C., Turk, M., & Höllerer, T. (2012) · International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI) · doi:10.1145/2371574.2371610 · Cited by 147
“(While state-ofthe-art SLAM-like systems [19, 27] have demonstrated impressive robustness, they still require the user to move the camera in a certain way especially during initialization.”
BackgroundMethodDense Reconstruction Using 3D Object Shape Priors
Dame, A., Prisacariu, V. A., Ren, C. Y., & Reid, I. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.170 · Cited by 135
“where g(u) is computed with respect to the reference image gradients, so that g is equal to 1 where Ir is uniform (see [15] for further details).”
BackgroundMethodInfluentialSurvey and evaluation of monocular visual-inertial SLAM algorithms for augmented reality
Li, J., Yang, B., Danpeng, C., Wang, N., Guofeng, Z., & Bao, H. (2019) · Virtual Reality & Intelligent Hardware · doi:10.1016/j.vrih.2019.07.002 · Cited by 151
“DSO uses a sparse and direct formulation proposed by [42], whereas previous works are mostly dense [43,44] .”
MethodDeepSLAM: A Robust Monocular SLAM System With Unsupervised Deep Learning
Li, R., Wang, S., & Gu, D. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.2982096 · Cited by 156
“sparse feature points [1]–[5] and photometric consistency of dense pixels [6]–[8].”
BackgroundMVDepthNet: Real-Time Multiview Depth Estimation Neural Network
Wang, K., & Shen, S. (2018) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2018.00037 · Cited by 157
Real-Time Large-Scale Dense 3D Reconstruction with Loop Closure
Kähler, O., Prisacariu, V. A., & Murray, D. W. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46484-8_30 · Cited by 151
“The same representation has been exploited in systems relying exclusively on RGB cameras without depth sensing [11, 12].”
BackgroundMethodCvišić, I., Ćesić, J., Marković, I., & Petrović, I. (2018) · Journal of Field Robotics · doi:10.1002/rob.21762 · Cited by 133
Dense 3D Object Reconstruction from a Single Depth View
Yang, B., Rosa, S., Markham, A., Trigoni, N., & Wen, H. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2868195 · Cited by 177
“recovered by dense feature extraction and matching [42], or by directly minimizing reprojection errors [43] from color images.”
BackgroundDeepV2D: Video to Depth with Differentiable Structure from MotionPreprint
Teed, Z., & Deng, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.04605 · Cited by 276
Chen, C., Zhu, H. J., Li, M., & You, S. (2018) · Robotics · doi:10.3390/robotics7030045 · Cited by 146
“There are many excellent visual SLAM methods that have improved the development of SLAM technologies, such as MonoSLAM [5], PTAM [8], RatSLAM [9], DTAM [10], KinectFusion [11], and ORB-SLAM [12].”
MethodA review of monocular visual odometry
He, M., Zhu, C., Huang, Q., Ren, B., & Liu, J. (2019) · The Visual Computer · doi:10.1007/s00371-019-01714-6 · Cited by 140
“The direct method of estimating camera motion based on the pixel gray invariance hypothesis has developed rapidly in recent years [20,28].”
MethodMonoFusion: Real-time 3D reconstruction of small scenes with a single web camera
Pradeep, V., Rhemann, C., Izadi, S., Zach, C., Bleyer, M., & Bathiche, S. (2013) · Proceedings - International Symposium on Mixed and Augmented Reality, ISMAR · doi:10.1109/ismar.2013.6671767 · Cited by 131
“Therefore most systems regularize depth maps using smoothness priors, and even optimize over multiple frames using photo-consistency, visibility, and shape priors, before performing surface reconstruction [30, 24, 23, 21].”
BackgroundInfluentialRobust RGB-D Odometry Using Point and Line Features
Lu, Y., & Song, D. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.448 · Cited by 126
“Although direct approaches can achieve superior accuracy by doing pixel-wise registration [12, 23, 37], their fundamental assumption on photoconsistency makes them sensitive to lighting condition changes.”
BackgroundAdvances in intelligent and autonomous navigation systems for small UAS
Bijjahalli, S., Sabatini, R., & Gardi, A. (2020) · Progress in Aerospace Sciences · doi:10.1016/j.paerosci.2020.100617 · Cited by 123
MobileFusion: Real-Time Volumetric Surface Reconstruction and Dense Tracking on Mobile Phones
Ondrúška, P., Kohli, P., & Izadi, S. (2015) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2015.2459902 · Cited by 135
“Minimization of the uncertainty aware photometric error defined above is achieved through simple Gauss-Newton gradient descent [3, 6, 17].”
MethodOctree-based fusion for realtime 3D reconstruction
Zeng, M., Zhao, F., Zheng, J., & Liu, X. (2012) · Graphical Models · doi:10.1016/j.gmod.2012.09.002 · Cited by 143
Map-Based Probabilistic Visual Self-Localization
Brubaker, M. A., Geiger, A., & Urtasun, R. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2453975 · Cited by 137
Probabilistic Semi-Dense Mapping from Highly Accurate Feature-Based Monocular SLAM
Mur-Artal, R., & Tardós, J. D. (2015) · Robotics: Science and Systems · doi:10.15607/rss.2015.xi.041 · Cited by 130
“After the excellent recent works [14, 3], there is the extended believe in the community that direct methods are more robust because they do not need features, and are more accurate because they use more information from the images.”
BackgroundMethodInfluentialStereoDRNet: Dilated Residual StereoNet
Chabra, R., Straub, J., Sweeney, C., Newcombe, R. A., & Fuchs, 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.2019.01206 · Cited by 130
“Total Variation denoising [19] has been used in cost filtering by methods described in [26], [16] and [14].”
BackgroundMethodSelf-citationVisual SLAM: What Are the Current Trends and What to Expect?
Tourani, A., Bavle, H., Sánchez-López, J. L., & Voos, H. (2022) · Sensors · doi:10.3390/s22239297 · Cited by 155
“A direct approach for measuring depth values and motion parameters for map construction was Dense Tracking and Mapping (DTAM) introduced by Newcombe et al. [20] in 2011.”
MethodSGS-SLAM: Semantic Gaussian Splatting for Neural Dense SLAM
Li, M., Liu, S., Zhou, H., Zhu, G., Cheng, N., Deng, T., & Wang, H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72751-1_10 · Cited by 236
“Traditional visual SLAM systems [6, 9, 27, 29, 32, 39] stand out Fig.”
BackgroundDirect Visual SLAM Using Sparse Depth for Camera-LiDAR System
Shin, Y.-S., Park, Y. S., & Kim, A. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8461102 · Cited by 115
“Instead of using a feature-based reprojection error model, they mainly use a photometric error model that considers the intensity difference of a pixel [4]–[6], [9], [16].”
MethodNeuroSLAM: a brain-inspired SLAM system for 3D environments
Yu, F., Shang, J., Hu, Y., & Milford, M. J. (2019) · Biological Cybernetics · doi:10.1007/s00422-019-00806-9 · Cited by 131
Efficient Octree-Based Volumetric SLAM Supporting Signed-Distance and Occupancy Mapping
Vespa, E., Nikolov, N., Grimm, M., Nardi, L., Kelly, P. H. J., & Leutenegger, S. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2792537 · Cited by 141
“Among the various dense SLAM systems, volumetric methods such as KinectFusion [24] rapidly became popular given the high-quality results achievable in real-time, comparable to what is attainable with more complex, inherently offline reconstruction methods such as [8][37].”
BackgroundInfluentialSimultaneous Localization and Mapping (SLAM) for Autonomous Driving: Concept and Analysis
Zheng, S., Wang, J., Rizos, C., Ding, W., & El‐Mowafy, A. (2023) · Remote Sensing · doi:10.3390/rs15041156 · Cited by 160
“Examples of direct SLAM include DTAM [97], LSD-SLAM [73], and SVO [98].”
BackgroundA Variational Approach to Video Registration with Subspace Constraints
Garg, R., Roussos, A., & Agapito, L. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-012-0607-7 · Cited by 126
Afif, M., Ayachi, R., Said, Y., Pissaloux, E. E., & Atri, M. (2020) · Neural Processing Letters · doi:10.1007/s11063-020-10197-9 · Cited by 132
“SLAM technique presents a popular way in order to implement localization techniques [14].”
MethodImage-based camera localization: an overview
Wu, Y., Tang, F., & Li, H. (2018) · Visual Computing for Industry Biomedicine and Art · doi:10.1186/s42492-018-0008-z · Cited by 132
Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding
Yang, Z., Wang, P., Wang, Y., Xu, W., & Nevatia, R. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11021-5_43 · Cited by 115
DeepSFM: Structure from Motion via Deep Bundle Adjustment
Wei, X., Zhang, Y., Li, Z., Fu, Y., & Xue, X. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58452-8_14 · Cited by 160
Chen, C., Wang, B., Lu, C. X., Trigoni, N., & Markham, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.12567 · Cited by 207
“In DeepTAM [237], both the depth and pose predictions from deep neural networks are introduced into a classical DTAM system [121], that is optimized globally by the back-end to achieve more accurate scene reconstruction and camera motion tracking.”
BackgroundMethod
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.