Accurate Optical Flow via Direct Cost Volume Processing

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2017)

引用 244|浏览185
暂无评分
摘要
We present an optical flow estimation approach that operates on the full four-dimensional cost volume. This direct approach shares the structural benefits of leading stereo matching pipelines, which are known to yield high accuracy. To this day, such approaches have been considered impractical due to the size of the cost volume. We show that the full four-dimensional cost volume can be constructed in a fraction of a second due to its regularity. We then exploit this regularity further by adapting semi-global matching to the four-dimensional setting. This yields a pipeline that achieves significantly higher accuracy than state-of-the-art optical flow methods while being faster than most. Our approach outperforms all published general-purpose optical flow methods on both Sintel and KITTI 2015 benchmarks.
更多
查看译文
关键词
structural benefits,Sintel,KITTI 2015 benchmarks,stereo matching pipelines,four-dimensional cost volume,optical flow estimation approach,direct cost volume processing,accurate optical flow,general-purpose optical flow methods,four-dimensional setting,semiglobal matching
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要