Existing stereo matching methods cannot guarantee both the computational accuracy and efficiency for ihe disparity estimation of large-scale or multi-view images.Hybrid tree method can obtain a disparity estimation fa...Existing stereo matching methods cannot guarantee both the computational accuracy and efficiency for ihe disparity estimation of large-scale or multi-view images.Hybrid tree method can obtain a disparity estimation fast with relatively low accuracy,while PatchMatch can give high-precision disparity value with relatively high computational cost.In this work,we propose the Hybrid Tree Guided PatchMatch which can calculate the disparity fast and accurate.Firstly,an initial disparity map is estimated by employing hybrid tree cost aggregation,which is used to constrain the label searching range of the PatchMatch.Furthermore,a reliable normal searching range for each current normal vector defined on the initial disparity map is calculated to refine the PatchMatch.Finally,an effective quantizing acceleration strategy is designed to decrease the matching computational cost of continuous disparity.Experimental results demonstrate that the disparity estimation based on our algorithm is better in binocular image benchmarks such as Middlebury and KITTI.We also provide the disparity estimation results for multi-view stereo in real scenes.展开更多
In multi-view stereo,unreliable matching in low-textured regions has a negative impact on the completeness of reconstructed models.Since the photometric consistency of low-textured regions is not discriminative under ...In multi-view stereo,unreliable matching in low-textured regions has a negative impact on the completeness of reconstructed models.Since the photometric consistency of low-textured regions is not discriminative under a local window,non-local information provided by the Markov Random Field(MRF)model can alleviate the matching ambiguity but is limited in continuous space with high computational complexity.Owing to its sampling and propagation strategy,PatchMatch multi-view stereo methods have advantages in terms of optimizing the continuous labeling problem.In this paper,we propose a novel method to address this problem,namely the Coarse-Hypotheses Guided Non-Local PAtchMatch Multi-View Stereo(CNLPA-MVS),which takes the advantages of both MRF-based non-local methods and PatchMatch multi-view stereo and compensates for their defects mutually.First,we combine dynamic programing(DP)and sequential propagation along scanlines in parallel to perform CNLPA-MVS,thereby obtaining the optimal depth and normal hypotheses.Second,we introduce coarse inference within a universal window provided by winner-takes-all to eliminate the stripe artifacts caused by DP and improve completeness.Third,we add a local consistency strategy based on the hypotheses of similar color pixels sharing approximate values into CNLPA-MVS for further improving completeness.CNLPA-MVS was validated on public benchmarks and achieved state-of-the-art performance with high completeness.展开更多
基金The National Natural Science of China(No.61572258,61771231,61772281,61672294)the Priority Academic Program Development of Jiangsu Higher Education Institutionsthe Qing Lan Project of Jiangsu Higher Education Institutions
文摘Existing stereo matching methods cannot guarantee both the computational accuracy and efficiency for ihe disparity estimation of large-scale or multi-view images.Hybrid tree method can obtain a disparity estimation fast with relatively low accuracy,while PatchMatch can give high-precision disparity value with relatively high computational cost.In this work,we propose the Hybrid Tree Guided PatchMatch which can calculate the disparity fast and accurate.Firstly,an initial disparity map is estimated by employing hybrid tree cost aggregation,which is used to constrain the label searching range of the PatchMatch.Furthermore,a reliable normal searching range for each current normal vector defined on the initial disparity map is calculated to refine the PatchMatch.Finally,an effective quantizing acceleration strategy is designed to decrease the matching computational cost of continuous disparity.Experimental results demonstrate that the disparity estimation based on our algorithm is better in binocular image benchmarks such as Middlebury and KITTI.We also provide the disparity estimation results for multi-view stereo in real scenes.
基金supported by the National Natural Science Foundation of China under Grant Nos.61732015,61932018,and 61472349the National Key Research and Development Program of China under Grant No.2017YFB0202203.
文摘In multi-view stereo,unreliable matching in low-textured regions has a negative impact on the completeness of reconstructed models.Since the photometric consistency of low-textured regions is not discriminative under a local window,non-local information provided by the Markov Random Field(MRF)model can alleviate the matching ambiguity but is limited in continuous space with high computational complexity.Owing to its sampling and propagation strategy,PatchMatch multi-view stereo methods have advantages in terms of optimizing the continuous labeling problem.In this paper,we propose a novel method to address this problem,namely the Coarse-Hypotheses Guided Non-Local PAtchMatch Multi-View Stereo(CNLPA-MVS),which takes the advantages of both MRF-based non-local methods and PatchMatch multi-view stereo and compensates for their defects mutually.First,we combine dynamic programing(DP)and sequential propagation along scanlines in parallel to perform CNLPA-MVS,thereby obtaining the optimal depth and normal hypotheses.Second,we introduce coarse inference within a universal window provided by winner-takes-all to eliminate the stripe artifacts caused by DP and improve completeness.Third,we add a local consistency strategy based on the hypotheses of similar color pixels sharing approximate values into CNLPA-MVS for further improving completeness.CNLPA-MVS was validated on public benchmarks and achieved state-of-the-art performance with high completeness.
