We propose SF2SE3, a novel approach to estimate scene dynamics in form of a segmentation into independently moving rigid objects and their SE(3)-motions. SF2SE3 operates on two consecutive stereo or RGB-D images. First, noisy scene flow is obtained by application of existing optical flow and depth estimation algorithms. SF2SE3 then iteratively (1) samples pixel sets to compute SE(3)-motion proposals, and (2) selects the best SE(3)-motion proposal with respect to a maximum coverage formulation. Finally, objects are formed by assigning pixels uniquely to the selected SE(3)-motions based on consistency with the input scene flow and spatial proximity. The main novelties are a more informed strategy for the sampling of motion proposals and a maximum coverage formulation for the proposal selection. We conduct evaluations on multiple datasets regarding application of SF2SE3 for scene flow estimation, object segmentation and visual odometry. SF2SE3 performs on par with the state of the art for scene flow estimation and is more accurate for segmentation and odometry.
翻译:我们建议SF2SE3, 一种以独立移动的僵硬物体及其SE(3)-动作进行分解的方式估计场景动态的新办法。 SF2SE3以两个连续立体或RGB-D图像运作。首先,利用现有光学流和深度估计算法获得噪音的场景流动。SF2SE3然后迭代:(1) 用于计算SE(3)-运动提案的样品像素组,和(2) 选择关于最大覆盖配方的最佳SE(3)-运动提议。最后,根据与输入场景流和空间相近性的一致性,将像素专门分配给选定的SE(3)-动作组。主要的新颖之处是,对运动提案的取样采取更知情的战略,对选择建议的最大范围进行设计。我们评估关于将SF2SE3应用于现场流估计、物体分割和视觉odology的多个数据集。SF2SE3在与现场流量估计的艺术状况相同的情况下进行测试,并且更精确地进行分解和分解。