Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks
This work addresses the challenge of selecting and tuning image matching models for 3D reconstruction in computer vision, but it is incremental as it focuses on evaluation rather than introducing new methods.
The paper evaluates image matching methods for 3D reconstruction using a structure-from-motion pipeline, finding that performance varies across datasets and highlighting limitations in both methods and benchmarks.
Three-dimensional (3D) reconstruction from two-dimensional images is an active research field in computer vision, with applications ranging from navigation and object tracking to segmentation and three-dimensional modeling. Traditionally, parametric techniques have been employed for this task. However, recent advancements have seen a shift towards learning-based methods. Given the rapid pace of research and the frequent introduction of new image matching methods, it is essential to evaluate them. In this paper, we present a comprehensive evaluation of various image matching methods using a structure-from-motion pipeline. We assess the performance of these methods on both in-domain and out-of-domain datasets, identifying key limitations in both the methods and benchmarks. We also investigate the impact of edge detection as a pre-processing step. Our analysis reveals that image matching for 3D reconstruction remains an open challenge, necessitating careful selection and tuning of models for specific scenarios, while also highlighting mismatches in how metrics currently represent method performance.