CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)(2018)

引用 65|浏览41
暂无评分
摘要
Recently, there has been a paradigm shift in stereo matching with learning-based methods achieving the best results on all popular benchmarks. The success of these methods is due to the availability of training data with ground truth; training learning-based systems on these datasets has allowed them to surpass the accuracy of conventional approaches based on heuristics and assumptions. Many of these assumptions, however, had been validated extensively and hold for the majority of possible inputs. In this paper, we generate a matching volume leveraging both data with ground truth and conventional wisdom. We accomplish this by coalescing diverse evidence from a bidirectional matching process via random forest classifiers. We show that the resulting matching volume estimation method achieves similar accuracy to purely data-driven alternatives on benchmarks and that it generalizes to unseen data much better. In fact, the results we submitted to the KITTI and ETH3D benchmarks were generated using a classifier trained on the Middlebury 2014 dataset.
更多
查看译文
关键词
CBMV,coalesced bidirectional matching volume,disparity estimation,paradigm shift,stereo matching,learning-based methods,training data,ground truth,conventional wisdom,coalescing diverse evidence,bidirectional matching process,random forest classifiers,resulting matching volume estimation method,data-driven alternatives,unseen data
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