DART: Dense Articulated Real-Time Tracking

By Tanner Schmidt, Richard A. Newcombe, Dieter Fox. 2014

156 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Mechanical Engineering

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

In Mechanical Engineering

Citations in the corpus

Habitat 2.0: Training Home Assistants to Rearrange their Habitat (2021, background): “Crafting an SPA pipeline for opening/closing unknown articulated containers is an open unsolved problem in robotics – involving detecting and tracking articulation [70, 71] without models, constrained full-body planning [72– 74] without hand engineering constraints, and designing controllers to hand”
Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience (2018, methodology): “After one SimOpt iteration, the robot can better control its gripper orientation, which leads to an accurate task execution. with DART [43] to continuously track the 3D positions of the peg in the swing-peg-in-hole task and the handle of the cab-inet drawer in the drawer opening task, as well as ini”
SE3-nets: Learning rigid body motion using deep neural networks (2016, methodology): “We use the DART motion tracker [32] to generate ground truth data associations for training.”
Graph-Structured Visual Imitation (2019, background): “To the best of our knowledge, this is the first work that uses human finger visual detectors as opposed to environment instrumentation [10] to track the demonstrator’s hand for visual imitation learning of object manipulations.”
Capturing Hands in Action Using Discriminative Salient Points and Physics Simulation (2015, background): “2009) has recently gained popularity with the ubiquity of RGB-D sensors (Oikonomidis et al. 2011a, 2012; Sridhar et al. 2013; Tompson et al. 2014; Schmidt et al. 2014; Qian et al. 2014).”
Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery (2021, background): “Existing work extracts parts from pairs of images [53, 51], point clouds [55] or videos [41, 27, 25].”
Reasoning About Liquids via Closed-Loop Simulation (2017, methodology): “1) Object Tracking: We use the software program DART [26] (Dense Articulated Real-Time Tracking) to track the objects in each interaction.”
SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Control (2018, background): “Unfortunately, for this pipeline to work, we need an external system (such as [6], [7]) capable of providing long range data-associations to measure progress.”
Robot arm pose estimation by pixel-wise regression of joint angles (2016, methodology): “Another approach is to use a 3D model of the robot to detect the arm in the image without the need for markers [6]–[9].”
Online Replanning in Belief Space for Partially Observable Task and Motion Problems (2019, methodology): “In our environment, the robot’s configuration as well as the door and drawer joint angles can be accurately estimated using our perception system [27], so we only maintain a point estimate for these variables.”
DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time (2015, background): “The best of these demonstrate high accuracy, real-time performance capture for tracking faces [16, 3], hands [21, 20], complete bodies [27], or general articulated objects [23, 33].”
Expressive Body Capture: 3D Hands, Face, and Body From a Single Image (2019, background): “There is also an extensive literature on modelling hands [39, 53, 57, 58, 68, 69, 71, 74, 75] and faces [4, 9, 11, 13, 14, 43, 63, 76, 79] in 3D but in isolation from the rest of the body.”
Self-supervised 6D Object Pose Estimation for Robot Manipulation (2019, methodology): “After computing the 3D points on the object, we optimize the pose by matching these points against the Signed Distance Function (SDF) of the object model as in [36].”
SE3-Pose-Nets: Structured Deep Dynamics Models for Visuomotor Planning and Control (2017, unknown): “Unfortunately, for this pipeline to work, we need an external system (such as [6], [7]) capable of providing long range data associations to measure progress.”
Manipulators and Manipulation in high dimensional spaces (2016, unknown): “While Kinect-style cameras focus on medium range sensing for full body tracking, other devices such as PrimeSense and LeapMotion[50] can be deployed for close-range tracking of hands [90].”
MuJoCo HAPTIX: A virtual reality system for hand manipulation (2015, unknown): “While Kinect-style cameras focus on medium range sensing for full body tracking, other devices such as PrimeSense and LeapMotion [18] can be deployed for close-range tracking of hands [19].”
ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact (2019, methodology): “Table III shows the median rank (across all objects) of the synthesized grasp, when grasps are ranked according to 1) the DART residual, and 2) GraspIt!’s Contact Energy metric [5].”
Embodied hands (2017, methodology): “Schmidt et al. [2014] voxelize each shape-primitive and compute a Signed Distance Function for the local coordinate frame (Fig.”
Compressed Voxel-Based Mapping Using Unsupervised Learning (2016, methodology): “SDF’s have been extensively applied to e.g. speeding up image-alignment [1] and raycasting [2] operations as well as collision detection [3], motion planning [4] and articulated-body motion tracking [5].”