Scale-Net: Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching
This addresses a key bottleneck in computer vision for applications like 3D reconstruction, but it is incremental as it builds on existing local feature methods.
The paper tackles the problem of poor image matching performance under large scale changes by proposing Scale-Net, which reduces scale differences before feature extraction, resulting in higher scale ratio estimation accuracy and improved performance in matching and pose estimation tasks.
Most image matching methods perform poorly when encountering large scale changes in images. To solve this problem, firstly, we propose a scale-difference-aware image matching method (SDAIM) that reduces image scale differences before local feature extraction, via resizing both images of an image pair according to an estimated scale ratio. Secondly, in order to accurately estimate the scale ratio, we propose a covisibility-attention-reinforced matching module (CVARM) and then design a novel neural network, termed as Scale-Net, based on CVARM. The proposed CVARM can lay more stress on covisible areas within the image pair and suppress the distraction from those areas visible in only one image. Quantitative and qualitative experiments confirm that the proposed Scale-Net has higher scale ratio estimation accuracy and much better generalization ability compared with all the existing scale ratio estimation methods. Further experiments on image matching and relative pose estimation tasks demonstrate that our SDAIM and Scale-Net are able to greatly boost the performance of representative local features and state-of-the-art local feature matching methods.