DTAM: Dense tracking and mapping in real-time

By Richard A. Newcombe, Steven J. Lovegrove, Andrew J. Davison. 2011

2,246 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

RLBench: The Robot Learning Benchmark & Learning Environment (2019, neutral): “However, if we would like a manipulation system to make use of a SLAM map, it is not currently clear what the best way to represent this map is: whether it be sparse [54], [55], dense [56], [57], or semidense [58].”
Unsupervised Learning of Depth and Ego-Motion from Video (2017, background): “Structure from motion The simultaneous estimation of structure and motion is a well studied problem with an established toolchain of techniques [12, 50, 38].”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, neutral): “Right: dense map of a desktop produced by DTAM [184].”
A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM (2014, background): “Multi-view stereo fusion of images has long been a research focus of the vision community, and has recently become feasible in real-time for reconstructing surfaces from monocular video [1], [2].”
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue (2016, methodology): “ it is a fair 8 Much like the log depth, inverse depth parametrization is less prone to the higher depth errors at very distant points and is used successfully in many stereo [13] and SLAM frameworks [27]. 12 Ravi Garg, Vijay Kumar B G, Gustavo Carneiro, Ian Reid Table 3. Comparison of proposed auto”
Kornia: an Open Source Differentiable Computer Vision Library for PyTorch (2019, background): “Multi-view reconstruction is a well understood problem with a good geometric model [21], and many approaches for matching and optimization [39, 8, 51], and some recent promising deep learning approaches [34].”
Cross-View Semantic Segmentation for Sensing Surroundings (2019, background): “re also integrating multiple local semantic maps into a semantic ﬂoor map for further applications. Note that there is a fundamental difference between the cross-view segmentation and the visual SLAM [28, 29]. While both estimate the spatial conﬁguration of an environment, our VPN aims at parsing th”
SVO: Fast semi-direct monocular visual odometry (2014, methodology): “With DTAM [15], a novel direct method was introduced that computes a dense depthmap for each keyframe through minimisation of a global, spatially-regularised energy functional .”
ElasticFusion: Dense SLAM Without A Pose Graph (2015, methodology): “We adopt an architecture which is typically found in realtime dense visual SLAM systems that alternates between tracking and mapping [15, 25, 9, 8, 2, 16].”
Pose Estimation for Augmented Reality: A Hands-On Survey (2016, positive): “2, dense or direct approaches such as DTAM [34], [90] or [137] allow each pixel contributing to the registration”
SemanticPaint (2015, methodology): “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].”
Elastic Fragments for Dense Scene Reconstruction (2013, background): “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].”
Learning to Explore using Active Neural SLAM (2020, background): “While sparse reconstruction can be done well with monocular RGB images (Mur-Artal and Tardós, 2017), dense mapping is inefﬁcient (Newcombe et al., 2011) or requires specialized scanners such as Kinect (Izadi et al., 2011).”
Visual Place Recognition: A Survey (2016, methodology): “The metric information within the topological place node can be stored as a sparse landmark map [2], [7], [76], or as a dense occupancy grid map [134] if depth information is extracted from the image data.”
DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency (2018, background): “Joint estimation of structure and camera pose from multiple images of a given scene is a long-standing problem [46,15,64].”
Image Retrieval for Image-Based Localization Revisited (2012, background): “With the widespread adoption of mobile camera phones, image-based localization has recently received increased attention as it enables many interesting applications such as mobile landmark recognition [4], real-time camera pose tracking [13, 21, 37], robot navigation [19], or community-based city re”
Visual SLAM algorithms: a survey from 2010 to 2016 (2017, methodology): “Basically, these methods [43, 46, 47] are designed for fast and online 3D modeling.”
Direct visual-inertial odometry with stereo cameras (2016, background): “More recently, direct methods have become popular also in a monocular environment, prominent examples include DTAM [26], SVO [10] and LSD-SLAM [4].”