A Variational Method for Scene Flow Estimation from Stereo Sequences

By Frédéric Huguet, Frederic Devernay. 2007

334 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): “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…”
Joint 3d Estimation of Vehicles and Scene Flow (2015, background): “…optical ﬂow estimation (Horn and 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…”
Kinecting the dots: Particle based scene flow from depth sensors (2011, methodology): “[1] and [9] are benchmark lines for comparison.”
Scene flow by tracking in intensity and depth data (2012, methodology): “Table 4 presents a summary of the errors of methods proposed in [16], [4] and [13] in comparison with the proposed algorithm in this work.”
FlowNet3D: Learning Scene Flow in 3D Point Clouds (2018, background): “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”
Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation (2014, background): “Several papers have tackled the problem of estimating the 3D flow-field [28,17,14,2].”
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].”
Efficient Dense Scene Flow from Sparse or Dense Stereo Data (2008, methodology): “This is about 500 times faster compared to the recent technique for joint scene flow computation in [7].”
Dense Semi-rigid Scene Flow Estimation from RGBD Images (2014, methodology): “The Middlebury stereo dataset [15] is commonly used as benchmark to compare scene flow methods [1,8,5,13].”
Piecewise Rigid Scene Flow (2013, methodology): “2D errors for the “sphere” sequence [10].”
Stereoscopic Scene Flow Computation for 3D Motion Understanding (2011, methodology): “For comparison, running the code from Huguet and Devernay (2007) generates an RMS error of 0.91 px and AAE of 6.83◦.”
3D scene flow estimation with a rigid motion prior (2011, methodology): “2D errors for the “sphere” sequence [10].”
3D Scene Flow Estimation with a Piecewise Rigid Scene Model (2015, methodology): “Possibly the ﬁrst to calculate geometry and ﬂow jointly in a two-view setup were Huguet and Devernay (2007), addressing the problem in a variational formulation.”
A primal-dual framework for real-time dense RGB-D scene flow (2015, methodology): “To allow for discontinuities in the motion field, Total Variation (TV) was adopted in [6] and [7], where they each present a unified variational formulation to compute the disparity and the motion field jointly.”
Multi-view Scene Flow Estimation: A View Centered Variational Approach (2010, methodology): “For comparison with the results of the scene flow algorithm proposed by Huguet et al.[7], we project our results for V and Z onto the images.”
Scene Flow from Depth and Color Images (2011, background): “Such estimation can be achieved using known disparity information [15] or in combination with disparity estimation [7, 8].”