TEASER: Fast and Certifiable Point Cloud Registration

Yang, Heng; Shi, Jingnan; Carlone, Luca

doi:10.1109/tro.2020.3033695

Cited by 469 publications

(410 citation statements)

References 90 publications

Supporting

Mentioning

408

Contrasting

Order By: Relevance

“…The consecutive states of the template are obtained by explicit modeling of Newtonian particles dynamics and solving for displacements and velocities of the particles with second-order ordinary differential equations (ODEs). In contrast to methods based on correspondences selection and filtering [13], [19], [29], FGA is a correspondence-free approach, i.e., its energy function is defined in terms of interactions between all template and reference points. Thus, our method is globallymultiply linked and has properties not found in other related algorithmic classes (e.g., high robustness to noise, versatile applicability of point masses and the fact that the locallyoptimal alignment is reached when the gravitational potential energy of the system is locally-minimal).…”

Section: A Contributionsmentioning

confidence: 99%

“…Some approaches [13], [19], [29], [35] first extract a sparse set of descriptive key points from point sets [36], [37] and then find optimal alignment parameters with a transformation estimation approach [38]- [42]. This policy does not use all available points and often leads to coarse alignments but, on the other hand, can result in a significantly improved initialization for other RPSR approaches [36].…”

Section: A From Transformation Estimation To Icpmentioning

confidence: 99%

See 1 more Smart Citation

Fast Gravitational Approach for Rigid Point Set Registration With Ordinary Differential Equations

et al. 2021

View full text Add to dashboard Cite

This article introduces a new physics-based method for rigid point set alignment called Fast Gravitational Approach (FGA). In FGA, the source and target point sets are interpreted as rigid particle swarms with masses interacting in a globally multiply-linked manner while moving in a simulated gravitational force field. The optimal alignment is obtained by explicit modeling of forces acting on the particles as well as their velocities and displacements with second-order ordinary differential equations of n-body motion. Additional alignment cues can be integrated into FGA through particle masses. We propose a smooth-particle mass function for point mass initialization, which improves robustness to noise and structural discontinuities. To avoid the quadratic complexity of all-to-all point interactions, we adapt a Barnes-Hut tree for accelerated force computation and achieve quasilinear complexity. We show that the new method class has characteristics not found in previous alignment methods such as efficient handling of partial overlaps, inhomogeneous sampling densities, and coping with large point clouds with reduced runtime compared to the state of the art. Experiments show that our method performs on par with or outperforms all compared competing deep-learning-based and general-purpose techniques (which do not take training data) in resolving transformations for LiDAR data and gains state-of-the-art accuracy and speed when coping with different data.

show abstract

Section: A Contributionsmentioning

confidence: 99%

Section: A From Transformation Estimation To Icpmentioning

confidence: 99%

Fast Gravitational Approach for Rigid Point Set Registration With Ordinary Differential Equations

et al. 2021

View full text Add to dashboard Cite

show abstract

“…A two hour long trajectory sampled at 10 Hz has close to three billion unique unordered pairs of sample points. Typical matching algorithms for generating constraints from a pair of sensor measurements, such as PnP [20], point cloud registration [45,54], or specialized neural networks [11,57], run on the order of tens to hundreds of milliseconds. Optimistically, densely matching all pairs would require close to one year on one CPU core.…”

Section: Sampling Inexact Loopsmentioning

confidence: 99%

Inexact Loops in Robotics Problems

Nelson¹

2021

Robotics: Science and Systems XVII

View full text Add to dashboard Cite

Loops are pervasive in robotics problems, appearing in mapping and localization, where one is interested in finding loop closure constraints to better approximate robot poses or other estimated quantities, as well as planning and prediction, where one is interested in the homotopy classes of the space through which a robot is moving. We generalize the standard topological definition of a loop to cases where a trajectory passes close to itself, but doesn't necessarily touch, giving a definition that is more practical for real robotics problems. This relaxation leads to new and useful properties of inexact loops, such as their ability to be partitioned into topologically connected sets closely matching the concept of a "loop closure", and the existence of simple and nonsimple loops. Building from these ideas, we introduce several ways to measure properties and quantities of inexact loops on a trajectory, such as the trajectory's "loop area" and "loop density", and use them to compare strategies for sampling representative inexact loops to build constraints in mapping and localization problems.• Which pairs of points constitute a single "loop"?• How often is a particular point near the rest of the trajectory or a particular segment?

show abstract

“…In turn, category-level perception renders the use of standard tools for pose estimation (from point cloud registration [30,55,87] to 2D-3D pose estimation [34,63,88]) ineffective, since they rely on the knowledge of the shape of the object. These limitations have triggered robotics and computer vision research on category-level 3D object pose estimation.…”

Section: Introductionmentioning

confidence: 99%

Optimal Pose and Shape Estimation for Category-level 3D Object Perception

Shi

Yang

Carlone

2021

Robotics: Science and Systems XVII

Self Cite

View full text Add to dashboard Cite

We consider a category-level perception problem, where one is given 3D sensor data picturing an object of a given category (e.g., a car), and has to reconstruct the pose and shape of the object despite intra-class variability (i.e., different car models have different shapes). We consider an active shape model, where -for an object category-we are given a library of potential CAD models describing objects in that category, and we adopt a standard formulation where pose and shape estimation are formulated as a non-convex optimization. Our first contribution is to provide the first certifiably optimal solver for pose and shape estimation. In particular, we show that rotation estimation can be decoupled from the estimation of the object translation and shape, and we demonstrate that (i) the optimal object rotation can be computed via a tight (small-size) semidefinite relaxation, and (ii) the translation and shape parameters can be computed in closed-form given the rotation. Our second contribution is to add an outlier rejection layer to our solver, hence making it robust to a large number of misdetections. Towards this goal, we wrap our optimal solver in a robust estimation scheme based on graduated non-convexity. To further enhance robustness to outliers, we also develop the first graph-theoretic formulation to prune outliers in category-level perception, which removes outliers via convex hull and maximum clique computations; the resulting approach is robust to 70 − 90% outliers. Our third contribution is an extensive experimental evaluation. Besides providing an ablation study on a simulated dataset and on the PASCAL3D+ dataset, we combine our solver with a deep-learned keypoint detector, and show that the resulting approach improves over the state of the art in vehicle pose estimation in the ApolloScape datasets.

show abstract

TEASER: Fast and Certifiable Point Cloud Registration

Cited by 469 publications

References 90 publications

Fast Gravitational Approach for Rigid Point Set Registration With Ordinary Differential Equations

Fast Gravitational Approach for Rigid Point Set Registration With Ordinary Differential Equations

Inexact Loops in Robotics Problems

Optimal Pose and Shape Estimation for Category-level 3D Object Perception

Contact Info

Product

Resources

About