Author manuscript, published in "IEEE Conference on Computer Vision and Pattern Recognition (CVPR '11) (2011)" Scene Flow Estimation by Growing Correspondence Seeds

Citations in the corpus

• A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation (2015, methodology): “The fastest method in KITTI’s scene flow top 7 is from Cech et al. [3] with a runtime of 2.4 seconds.”
• Are we ready for autonomous driving? The KITTI vision benchmark suite (2012, unknown): “For stereo matching, we run global [26, 37, 46], semiglobal [23], local [5, 20, 38] and seed-growing [27, 10, 9] methods.”
• Continuous Markov Random Fields for Robust Stereo Estimation (2012, unknown): “90 % GCSF [39] 20.”
• Piecewise Rigid Scene Flow (2013, background): “Moreover, it strongly outperforms another 3D scene flow technique [7], even on its semi-dense output.”
• 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].”
• A primal-dual framework for real-time dense RGB-D scene flow (2015, methodology): “[14] presented a seed growing algorithm to compute scene flow in a stereo setup which represents a good trade-off between local and global methods with respect to accuracy and running time.”
• 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”