Enhancing Multi-view Stereo with Contrastive Matching and Weighted Focal Loss

TL;DR

This paper introduces a novel contrastive matching loss and a weighted focal loss to improve the accuracy and completeness of learning-based multi-view stereo methods, achieving state-of-the-art results.

Contribution

The paper proposes a contrastive matching loss and a weighted focal loss to enhance multi-view stereo networks, addressing accuracy and completeness issues.

Findings

Achieves state-of-the-art performance on multiple datasets.

Significant improvement over baseline networks.

Effective in handling low-confidence pixels.

Abstract

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.