Scene Particles: Unregularized Particle Based Scene Flow Estimation.

29 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, background): “In contrast to optical flow which provides the projection of the scene motion onto the image plane, scene flow [41, 6, 26, 8, 11, 37, 32] estimates the actual 3D motion field.”
A primal-dual framework for real-time dense RGB-D scene flow (2015, methodology): “As in similar works [16], two error measurements are compared: the 3D average angle error (AAE) expressed in degrees and the normalized root mean square error of the velocity magnitude (NRMS-V), where the maximum magnitude of the motion ﬁeld (MAX-V) is used for normalization.”
SphereFlow: 6 DoF Scene Flow from RGB-D Pairs (2014, methodology): “In Figures 7, 8, and 9, we show analogous results for large displacement Kinect data sets of varying complexity, and compare against the results of the RGB-D scene flow techniques of Hadfield and Bowden [11], Herbst et al.”