E3CM: Epipolar-Constrained Cascade Correspondence Matching
This addresses the need for reliable matching in 3D vision tasks without large labeled datasets, though it appears incremental as it builds on existing deep learning and epipolar constraint techniques.
The paper tackles the problem of accurate and robust correspondence matching for 3D computer vision by introducing E3CM, a method that uses pre-trained CNNs without annotated data and achieves superior performance over existing methods in experiments.
Accurate and robust correspondence matching is of utmost importance for various 3D computer vision tasks. However, traditional explicit programming-based methods often struggle to handle challenging scenarios, and deep learning-based methods require large well-labeled datasets for network training. In this article, we introduce Epipolar-Constrained Cascade Correspondence (E3CM), a novel approach that addresses these limitations. Unlike traditional methods, E3CM leverages pre-trained convolutional neural networks to match correspondence, without requiring annotated data for any network training or fine-tuning. Our method utilizes epipolar constraints to guide the matching process and incorporates a cascade structure for progressive refinement of matches. We extensively evaluate the performance of E3CM through comprehensive experiments and demonstrate its superiority over existing methods. To promote further research and facilitate reproducibility, we make our source code publicly available at https://mias.group/E3CM.