Learning Optical Flow, Depth, and Scene Flow without Real-World Labels
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2022.3145057
Abstract: Self-supervised monocular depth estimation enables robots to learn 3D perception from raw video streams. This scalable approach leverages projective geometry and ego-motion to learn via view synthesis, assuming the world is mostly static. Dynamic scenes,… read more here.
Keywords: scene flow; depth scene; optical flow; flow ... See more keywords
Self-Supervised Scene Flow Estimation With 4-D Automotive Radar
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2022.3187248
Abstract: Scene flow allows autonomous vehicles to reason about the arbitrary motion of multiple independent objects which is the key to long-term mobile autonomy. While estimating the scene flow from LiDAR has progressed recently, it remains… read more here.
Keywords: flow estimation; scene flow; radar; scene ... See more keywords
Estimation and Propagation: Scene Flow Prediction on Occluded Point Clouds
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2022.3215019
Abstract: With the development of 3D sensors, estimating the point movements between two consecutive point clouds is becoming increasingly attractive. Using correlation-based deep neural networks, existing solutions achieve promising performance. However, these methods couple the non-occluded… read more here.
Keywords: occluded points; point clouds; scene flow; flow ... See more keywords
PT-FlowNet: Scene Flow Estimation on Point Clouds With Point Transformer
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2023.3254431
Abstract: As a low-level task of 3D perception, scene flow is a fundamental representation of dynamic scenes and provides non-rigid motion descriptions for the objects in the 3D environment, which can strongly support many upper-level applications.… read more here.
Keywords: point clouds; point transformer; flow estimation; scene flow ... See more keywords
High-Speed Scene Flow on Embedded Commercial Off-the-Shelf Systems
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Industrial Informatics"
DOI: 10.1109/tii.2018.2864173
Abstract: Scene flow is an essential part of a stereo-based perception system for autonomous driving and mobile robotics. As in most of these platforms, the computing resource is limited but the computing requirement is high, embedded… read more here.
Keywords: scene; commercial shelf; scene flow; speed ... See more keywords
3-D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Industrial Informatics"
DOI: 10.1109/tii.2022.3210560
Abstract: 3-D scene flow characterizes how the points at the current time flow to the next time in the 3-D Euclidean space, which possesses the capacity to infer autonomously the nonrigid motion of all objects in… read more here.
Keywords: flow estimation; scene flow; lidar; scene ... See more keywords
Scene Flow Estimation Based on Adaptive Anisotropic Total Variation Flow-Driven Method
Sign Up to like & getrecommendations! Published in 2018 at "Mathematical Problems in Engineering"
DOI: 10.1155/2018/4908273
Abstract: Scene flow estimation based on disparity and optical flow is a challenging task. We present a novel method based on adaptive anisotropic total variation flow-driven method for scene flow estimation from a calibrated stereo image… read more here.
Keywords: scene flow; flow estimation; anisotropic; scene ... See more keywords
A 3D LiDAR odometry for UGVs using coarse-to-fine deep scene flow estimation
Sign Up to like & getrecommendations! Published in 2022 at "Transactions of the Institute of Measurement and Control"
DOI: 10.1177/01423312221105165
Abstract: Light detection and ranging (LiDAR) odometry plays a crucial role in autonomous mobile robots and unmanned ground vehicles (UGVs). This paper presents a deep learning–based odometry system using two successive three-dimensional (3D) point clouds to… read more here.
Keywords: coarse fine; scene flow; odometry; lidar odometry ... See more keywords
Event-Based 3D Motion Flow Estimation Using 4D Spatio Temporal Subspaces Properties
Sign Up to like & getrecommendations! Published in 2017 at "Frontiers in Neuroscience"
DOI: 10.3389/fnins.2016.00596
Abstract: State of the art scene flow estimation techniques are based on projections of the 3D motion on image using luminance—sampled at the frame rate of the cameras—as the principal source of information. We introduce in… read more here.
Keywords: motion; scene flow; event based; flow estimation ... See more keywords