.png){kind=icon}
Return
FeatFlow: Learning geometric features for 3D motion estimation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2020.107574.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
3D motion estimation is an important prerequisite for the autonomous operation of vehicles and robots in dynamic environments. This work presents FeatFlow, a novel neural network architecture to estimate 3D motions from unstructured point clouds. Specifically, we learn deep geometric features to estimate the dense scene flow and the ego-motion of the platform. We build a scene flow estimation pipeline by an encoder-decoder architecture which comprises three novel modules: feature extractor, motion embedder, and flow decoder. By using a point-score layer to assign scores to the extracted features in a learning procedure, the feature extractor effectively extracts keypoints and features that are most significant for estimating the relative transformation between two consecutive point clouds. The whole model adaptively learns the required robust descriptors to represent a variety of point motions at the object or scene level. We evaluated our approach on synthetic data from FlyingThings3D, and real-world LiDAR scans from KITTI and Oxford RobotCar. Our network successfully generalizes to datasets with different patterns, outperforming various baselines and achieving state-of-the-art performance. (C) 2020 Elsevier Ltd. All rights reserved.
Keywords:
Feature learning
Motion estimation
Point clouds
Scene flow
Scan-matching
Ego-motion
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
ShareSaveShareSaveRobust and direct estimation of 3-D motion and scene depth from stereo image sequences.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveShareSaveShareSaveNonrigid Point Set Registration With Robust Transformation Learning Under Manifold Regularization
PREAI
ShareSaveShareSave
View more