论文标题
增强具有对比匹配和加权焦点损失的多视图立体声
Enhancing Multi-view Stereo with Contrastive Matching and Weighted Focal Loss
论文作者
论文摘要
基于学习的多视图立体声（MVS）方法取得了令人印象深刻的进步，并且近年来超过了传统方法。但是，它们的准确性和完整性仍在挣扎。在本文中，我们提出了一种新方法，以增强受对比度学习和功能匹配启发的现有网络的性能。首先，我们提出了一个对比匹配损失（CML），该损失将正确的匹配点视为正样样本，并将其他点视为阴性样本，并根据特征的相似性计算对比度损失。我们进一步提出了一个加权局灶性损失（WFL），以提高分类能力，从而削弱了根据预测的置信度，在不重要的区域中低符合像素对损失的贡献。在DTU，坦克和寺庙和混合物数据集上进行的广泛实验显示，我们的方法可实现最先进的性能，并且对基线网络进行了显着改善。
Learning-based multi-view stereo (MVS) methods have made impressive progress and surpassed traditional methods in recent years. However, their accuracy and completeness are still struggling. In this paper, we propose a new method to enhance the performance of existing networks inspired by contrastive learning and feature matching. First, we propose a Contrast Matching Loss (CML), which treats the correct matching points in depth-dimension as positive sample and other points as negative samples, and computes the contrastive loss based on the similarity of features. We further propose a Weighted Focal Loss (WFL) for better classification capability, which weakens the contribution of low-confidence pixels in unimportant areas to the loss according to predicted confidence. Extensive experiments performed on DTU, Tanks and Temples and BlendedMVS datasets show our method achieves state-of-the-art performance and significant improvement over baseline network.
