MSF-Net: Multi-Stage Feature Extraction and Fusion for Robust Photometric Stereo
This addresses the challenge of robust surface normal reconstruction in photometric stereo for computer vision applications, representing an incremental improvement over existing methods.
The paper tackled the problem of inaccurate feature extraction and lack of interaction in learning-based photometric stereo, proposing MSF-Net to improve surface normal estimation, with results showing it significantly surpasses previous state-of-the-art methods on the DiLiGenT benchmark.
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.