3D scene flow estimation with a rigid motion prior

By Christoph Vogel, Konrad Schindler, Stefan Roth. 2011

111 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, methodology): “These methods either extracted features from one modality: depth [65, 78, 42, 77, 37, 67, 68] or RGB [6, 40, 46] or skeleton [76, 75, 22, 13, 57, 72, 85, 8, 47], or fuse the features extracted separately from them at a later stage [ In contrast, we propose to adopt scene ﬂow for 3D action…”
3D Scene Flow Estimation with a Piecewise Rigid Scene Model (2015, methodology): “15 we extend our standard 2D proposal set by adding proposals from 3D scene ﬂow methods ( 3D-Props ), namely L 1 -regularized 3D scene ﬂow (Basha et al. 2010) and locally rigid 3D scene ﬂow (Vogel et al. 2011).”
Discrete-Continuous Depth Estimation from a Single Image (2014, background): “In this context, 3D scene flow is one of the most popular and mature approaches to depth estimation [3, 4, 29].”
Object scene flow for autonomous vehicles (2015, methodology): “Therefore, synthetic renderings of spheres [18, 32], primitives [1, 6, 36] or simple street scenes [25, 38, 39] are typically employed to measure quantitative performance.”
Scene flow by tracking in intensity and depth data (2012, methodology): “[33] regularize the problem by encouraging a locally rigid 3D motion field, outperforming TV regularization.”
Piecewise Rigid Scene Flow (2013, methodology): “, encouraging locally rigid motion [22] as is common to many scenes.”
FlowNet3D: Learning Scene Flow in 3D Point Clouds (2018, methodology): “Since this seminal work, many others have tried to jointly estimate structure and motion from stereoscopic images [12, 18, 34, 26, 5, 33, 28, 29, 1, 30, 16], mostly in a variational setting with regularizations for smoothness of motion and structure [12, 1, 26], or with assumption of the rigidity of”
Joint 3d Estimation of Vehicles and Scene Flow (2015, background): “…Schunck, 1980), the problem is often formulated in a coarse-to-ﬁne variational setting (Basha et al., 2013, Huguet and Devernay, 2007, Pons et al., 2007, Valgaerts et al., 2010, Wedel et al., 2011, Vogel et al., 2011) and local regularizers are leveraged to encourage smoothness in depth and motion.”
A primal-dual framework for real-time dense RGB-D scene flow (2015, background): “Moreover, some of the most recent works with stereo cameras [9], [10] propose to exploit the fact that in most realistic scenarios the image motion is composed of several rigid body motions, and 2015 IEEE International Conference on Robotics and Automation (ICRA) Washington State Convention Center S”
SphereFlow: 6 DoF Scene Flow from RGB-D Pairs (2014, methodology): “RGB scene flow methods include Huguet and Devernay [15], Min and Sohn [18], Zhang and Kambhamettu [32], Basha et al. [4], ˇ Cech et al. [25], and Vogel et al. [27].”
Dense Semi-rigid Scene Flow Estimation from RGBD Images (2014, background): “or by assuming a local rigidity of the scene [19].”