当前位置: X-MOL 学术J. Comput. Sci. Tech. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
CNLPA-MVS: Coarse-Hypotheses Guided Non-Local PatchMatch Multi-View Stereo
Journal of Computer Science and Technology ( IF 1.2 ) Pub Date : 2021-05-31 , DOI: 10.1007/s11390-021-1299-7
Qitong Zhang , Shan Luo , Lei Wang , Jieqing Feng

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.



中文翻译:

CNLPA-MVS:粗假设引导的非局部 PatchMatch 多视图立体

在多视图立体中,低纹理区域的不可靠匹配对重建模型的完整性有负面影响。由于低纹理区域的光度一致性在局部窗口下没有辨别力,马尔可夫随机场(MRF)模型提供的非局部信息可以缓解匹配模糊性,但在计算复杂度高的连续空间中受到限制。由于其采样和传播策略,PatchMatch 多视图立体方法在优化连续标记问题方面具有优势。在本文中,我们提出了一种新方法来解决这个问题,即粗假设引导的非局部 PatchMatch 多视图立体 (CNLPA-MVS),它利用了基于 MRF 的非局部方法和 PatchMatch 多视图立体的优点,并相互弥补了它们的缺陷。首先,我们结合动态规划(DP)和沿扫描线的顺序传播并行执行CNLPA-MVS,从而获得最佳深度和正态假设。其次,我们在由赢家通吃提供的通用窗口中引入粗推,以消除由 DP 引起的条纹伪影并提高完整性。第三,我们将基于相似颜色像素共享近似值的假设的局部一致性策略添加到 CNLPA-MVS 中,以进一步提高完整性。CNLPA-MVS 在公共基准测试中得到验证,并以高度的完整性实现了最先进的性能。我们将动态规划 (DP) 和沿扫描线的顺序传播并行地结合起来执行 CNLPA-MVS,从而获得最佳深度和正态假设。其次,我们在由赢家通吃提供的通用窗口中引入粗推,以消除由 DP 引起的条纹伪影并提高完整性。第三,我们将基于相似颜色像素共享近似值的假设的局部一致性策略添加到 CNLPA-MVS 中,以进一步提高完整性。CNLPA-MVS 在公共基准测试中得到验证,并以高度的完整性实现了最先进的性能。我们将动态规划 (DP) 和沿扫描线的顺序传播并行地结合起来执行 CNLPA-MVS,从而获得最佳深度和正态假设。其次,我们在由赢家通吃提供的通用窗口中引入粗推,以消除由 DP 引起的条纹伪影并提高完整性。第三,我们将基于相似颜色像素共享近似值的假设的局部一致性策略添加到 CNLPA-MVS 中,以进一步提高完整性。CNLPA-MVS 在公共基准测试中得到验证,并以高度的完整性实现了最先进的性能。我们在由赢家通吃提供的通用窗口中引入粗略推理,以消除由 DP 引起的条纹伪影并提高完整性。第三,我们将基于相似颜色像素共享近似值的假设的局部一致性策略添加到 CNLPA-MVS 中,以进一步提高完整性。CNLPA-MVS 在公共基准测试中得到验证,并以高度的完整性实现了最先进的性能。我们在由赢家通吃提供的通用窗口中引入粗略推理,以消除由 DP 引起的条纹伪影并提高完整性。第三,我们将基于相似颜色像素共享近似值的假设的局部一致性策略添加到 CNLPA-MVS 中,以进一步提高完整性。CNLPA-MVS 在公共基准测试中得到验证,并以高度的完整性实现了最先进的性能。

更新日期:2021-06-15
down
wechat
bug