PointFlowNet: Learning Representations for Rigid Motion Estimation From Point Clouds

This paper proposes an approach to improve the reality effect of fabric dynamic simulation based on mass-spring model. The major problem encountered in fabric dynamic simulation is the difficulty to determine the characteristic of material and the changes of deformation force. To solve this problem, feature points motion constraints are introduced into the mass-spring model. This paper also establishes a framework of an approach to recover feature points motion based on non-rigid motion trajectory representation model. Then the recovered 3D estimation of the fabric feature points are used to adjust the simulation computing process of the mass-spring model, and simulation results with good reality are obtained. The experimental results for fabric dynamic simulation demonstrate the feasibility of improving the reality effect by the proposed motion-estimation-drive approach.

Download Full-text

Self-supervised learning-based diffeomorphic non-rigid motion estimation for fast motion-compensated coronary MR angiography

Magnetic Resonance Imaging ◽

10.1016/j.mri.2021.10.004 ◽

2021 ◽

Author(s):

Camila Munoz ◽

Haikun Qi ◽

Gastao Cruz ◽

Thomas Kuestner ◽

René M. Botnar ◽

...

Keyword(s):

Motion Estimation ◽

Supervised Learning ◽

Mr Angiography ◽

Rigid Motion ◽

Fast Motion ◽

Coronary Mr Angiography

Download Full-text

Registration of spatio-temporal point clouds of plants for phenotyping

PLoS ONE ◽

10.1371/journal.pone.0247243 ◽

2021 ◽

Vol 16 (2) ◽

pp. e0247243

Author(s):

Nived Chebrolu ◽

Federico Magistri ◽

Thomas Läbe ◽

Cyrill Stachniss

Keyword(s):

Plant Traits ◽

Scale Up ◽

Rigid Motion ◽

Point Clouds ◽

Plant Performance ◽

Sensor Data ◽

Plant Phenotyping ◽

Compact Representation ◽

3D Point Clouds ◽

Over Time

Plant phenotyping is a central task in crop science and plant breeding. It involves measuring plant traits to describe the anatomy and physiology of plants and is used for deriving traits and evaluating plant performance. Traditional methods for phenotyping are often time-consuming operations involving substantial manual labor. The availability of 3D sensor data of plants obtained from laser scanners or modern depth cameras offers the potential to automate several of these phenotyping tasks. This automation can scale up the phenotyping measurements and evaluations that have to be performed to a larger number of plant samples and at a finer spatial and temporal resolution. In this paper, we investigate the problem of registering 3D point clouds of the plants over time and space. This means that we determine correspondences between point clouds of plants taken at different points in time and register them using a new, non-rigid registration approach. This approach has the potential to form the backbone for phenotyping applications aimed at tracking the traits of plants over time. The registration task involves finding data associations between measurements taken at different times while the plants grow and change their appearance, allowing 3D models taken at different points in time to be compared with each other. Registering plants over time is challenging due to its anisotropic growth, changing topology, and non-rigid motion in between the time of the measurements. Thus, we propose a novel approach that first extracts a compact representation of the plant in the form of a skeleton that encodes both topology and semantic information, and then use this skeletal structure to determine correspondences over time and drive the registration process. Through this approach, we can tackle the data association problem for the time-series point cloud data of plants effectively. We tested our approach on different datasets acquired over time and successfully registered the 3D plant point clouds recorded with a laser scanner. We demonstrate that our method allows for developing systems for automated temporal plant-trait analysis by tracking plant traits at an organ level.

Download Full-text