arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.08313cs.CV
收藏

基于语义分割的级联场景流预测

Cascaded Scene Flow Prediction using Semantic Segmentation

Brown University(布朗大学);NVIDIA(英伟达);UC Irvine(加州大学欧文分校)

Zhile Ren, Deqing Sun, Jan Kautz, Erik B. Sudderth

摘要:

给定来自一对立体相机的两个连续帧,3D场景流方法同时估计所观察场景的3D几何形状和运动。许多现有的方法使用超像素进行正则化,但可能会预测刚性移动对象内部不一致的形状和运动。相反,我们假设场景由在静态背景前面刚性移动的前景对象组成,并使用语义线索来产生像素精确的场景流估计。我们的级联分类框架通过迭代地改进语义分割掩模、立体对应、3D刚性运动估计和光流场来精确地建模3D场景。我们在具有挑战性的KITTI自动驾驶基准上评估了我们的方法,并表明考虑分段车辆的运动会带来最先进的性能。

英文摘要:

Given two consecutive frames from a pair of stereo cameras, 3D scene flow methods simultaneously estimate the 3D geometry and motion of the observed scene. Many existing approaches use superpixels for regularization, but may predict inconsistent shapes and motions inside rigidly moving objects. We instead assume that scenes consist of foreground objects rigidly moving in front of a static background, and use semantic cues to produce pixel-accurate scene flow estimates. Our cascaded classification framework accurately models 3D scenes by iteratively refining semantic segmentation masks, stereo correspondences, 3D rigid motion estimates, and optical flow fields. We evaluate our method on the challenging KITTI autonomous driving benchmark, and show that accounting for the motion of segmented vehicles leads to state-of-the-art performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑