Scene Flow Estimation
31 papers with code • 3 benchmarks • 4 datasets
Scene Flow Estimation is the task of obtaining 3D structure and 3D motion of dynamic scenes, which is crucial to environment perception, e.g., in the context of autonomous navigation.
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.
HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds
We present a novel deep neural network architecture for end-to-end scene flow estimation that directly operates on large-scale 3D point clouds.
Finally, we showcase the performance of transport-enhanced registration models on a wide range of challenging tasks: rigid registration for partial shapes; scene flow estimation on the Kitti dataset; and nonparametric registration of lung vascular trees between inspiration and expiration.
Estimation of 3D motion in a dynamic scene from a temporal pair of images is a core task in many scene understanding problems.
This paper introduces a first effort to apply a deep learning method for direct estimation of scene flow by presenting a fully convolutional neural network with an encoder-decoder (ED) architecture.
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation
Making use of the estimated occlusions, we also show improved results on motion segmentation and scene flow estimation.
Performance on the five tasks of depth estimation, optical flow estimation, odometry, moving object segmentation and scene flow estimation shows that our approach outperforms other SoTA methods.
In the last few years, convolutional neural networks (CNNs) have demonstrated increasing success at learning many computer vision tasks including dense estimation problems such as optical flow and stereo matching.
The problem of Scene flow estimation in depth videos has been attracting attention of researchers of robot vision, due to its potential application in various areas of robotics.