2024/01/25 by Andrea Conti, Conti, Andrea, Matteo Poggi +5 · 2 citations
Computer Science · Mathematics · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Epipolar geometry #FOS: Computer and information sciences #Focus (optics) #Image (mathematics) #Matching (statistics) #Mathematics #Metric (unit) #Range (aeronautics) #Selection (genetic algorithm) #Video Coding and Compression Technologies
paper · pdf · doi:10.48550/arxiv.2401.14401
openalex publication_date 2024/01/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Methods for 3D reconstruction from posed frames require prior knowledge about the scene metric range, usually to recover matching cues along the epipolar lines and narrow the search range. However, such prior might not be directly available or estimated inaccurately in real scenarios -- e.g., outdoor 3D reconstruction from video sequences -- therefore heavily hampering performance. In this paper, we focus on multi-view depth estimation without requiring prior knowledge about the metric range of the scene by proposing RAMDepth, an efficient and purely 2D framework that reverses the depth estimation and matching steps order. Moreover, we demonstrate the capability of our framework to provide rich insights about the quality of the views used for prediction. Additional material can be found on our project page https://andreaconti.github.io/projects/rangeagnosticmultiviewdepth.