2023/05/18 by Dongxu Zhao, Zhao, Dongxu, Daniel Lichy +7 · 2 citations
Computer Science · #Advanced Vision and Imaging #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Enhancement Techniques
paper · pdf · doi:10.48550/arxiv.2305.11167
openalex publication_date 2023/05/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose a fast and generalizable solution to Multi-view Photometric Stereo (MVPS), called MVPSNet. The key to our approach is a feature extraction network that effectively combines images from the same view captured under multiple lighting conditions to extract geometric features from shading cues for stereo matching. We demonstrate these features, termed `Light Aggregated Feature Maps' (LAFM), are effective for feature matching even in textureless regions, where traditional multi-view stereo methods fail. Our method produces similar reconstruction results to PS-NeRF, a state-of-the-art MVPS method that optimizes a neural network per-scene, while being 411× faster (105 seconds vs. 12 hours) in inference. Additionally, we introduce a new synthetic dataset for MVPS, sMVPS, which is shown to be effective to train a generalizable MVPS method.