Stereoscopic Scene Flow Computation for 3D Motion Understanding

By Andreas Wedel, Thomas Brox, Tobi Vaudrey, Clemens Rabe, Uwe Franke, Daniel Cremers. 2011

197 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition with Convolutional Neural Networks (2017, methodology): “Since this work, several methods [64, 57, 44] have been proposed based on stereo or multiple view camera systems.”
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation (2015, background): “[25] they decoupled the disparity estimation and replaced it by the depth values of RGBD videos.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “In addition, Wedel et al. (2011) propose a solution for varying lighting conditions based on residual images and provide an uncertainty measure which is shown to be useful for object segmentation.”
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.”
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation (2018, methodology): “[45] and was later dominated by variational methods [15] [33] [47].”
Learning the Depths of Moving People by Watching Frozen People (2019, methodology): “Depth information captured from RGBD sensors or stereo cameras has been widely used for 3D modeling of dynamic scenes [1], [2], [7], [18], [20], [32], [38], [51], [59], [66].”
Learning Motion Patterns in Videos (2016, methodology): “, 3D motion field in a scene [37], is another form of motion estimation, but is computed with additional information, such as disparity values computed from stereo images [15, 40], or estimated 3D scene models [38].”
A primal-dual framework for real-time dense RGB-D scene flow (2015, background): “However, other authors claimed that decoupling this two sub-problems is indeed advantageous and developed algorithms [8] that make the most of this decoupling to efficiently solve the global problem, combining FPGA and GPU for disparity and scene flow estimation, respectively, and leading to real-ti”
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.”