ConDL: Detector-Free Dense Image Matching
This work addresses the problem of robust image matching for computer vision applications, offering a detector-free approach that could simplify pipelines, though it appears incremental as it builds on contrastive learning and synthetic data training.
The paper tackles dense image correspondence estimation by introducing a fully convolutional deep-learning framework that generates dense feature maps for matching across images, achieving robust matching under distortions like perspective changes and illumination variations without requiring a keypoint detector.
In this work, we introduce a deep-learning framework designed for estimating dense image correspondences. Our fully convolutional model generates dense feature maps for images, where each pixel is associated with a descriptor that can be matched across multiple images. Unlike previous methods, our model is trained on synthetic data that includes significant distortions, such as perspective changes, illumination variations, shadows, and specular highlights. Utilizing contrastive learning, our feature maps achieve greater invariance to these distortions, enabling robust matching. Notably, our method eliminates the need for a keypoint detector, setting it apart from many existing image-matching techniques.