提出多阶段特征提取与融合网络，提升复杂表面法线估计精度
MSF-Net: Multi-Stage Feature Extraction and Fusion for Robust Photometric Stereo
- 设计多阶段特征提取与选择性更新机制，减少冗余特征
- 在DiLiGenT数据集上法线估计误差显著低于现有方法
- 适合需要高精度三维重建的科研与工业应用
光度立体技术通过不同光照条件下的图像获取表面法线。然而，现有基于学习的方法常无法在多阶段有效捕捉特征，且特征间交互不足，导致在褶皱、边缘等细节区域提取冗余信息。为此，本文提出MSF-Net框架，采用多阶段特征提取与选择性更新策略，以获取高质量特征信息，对精确构建表面法线至关重要。同时，设计了特征融合模块增强不同层级特征间的交互。在DiLiGenT基准测试中，所提方法显著优于现有最先进方法，在表面法线估计精度上表现突出。
原文摘要 · Abstract (English)
Photometric stereo is a technique aimed at determining surface normals through the utilization of shading cues derived from images taken under different lighting conditions. However, existing learning-based approaches often fail to accurately capture features at multiple stages and do not adequately promote interaction between these features. Consequently, these models tend to extract redundant features, especially in areas with intricate details such as wrinkles and edges. To tackle these issues, we propose MSF-Net, a novel framework for extracting information at multiple stages, paired with selective update strategy, aiming to extract high-quality feature information, which is critical for accurate normal construction. Additionally, we have developed a feature fusion module to improve the interplay among different features. Experimental results on the DiLiGenT benchmark show that our proposed MSF-Net significantly surpasses previous state-of-the-art methods in the accuracy of surface normal estimation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。