SA-DNet: A on-demand semantic object registration network adapting to non-rigid deformation

TL;DR

SA-DNet is a novel deep learning framework that improves non-rigid infrared-visible image registration by focusing on semantic regions of interest, enabling task-specific and robust feature matching for better image fusion.

Contribution

The paper introduces SA-DNet, a semantic-aware network with modules for on-demand feature matching in semantic regions, enhancing registration accuracy under non-rigid distortions.

Findings

SA-DNet outperforms five state-of-the-art methods in robustness to non-rigid distortions.

The method achieves more accurate semantic registration for infrared and visible images.

SA-DNet enables task-specific registration by selecting semantic objects as needed.

Abstract

As an essential processing step before the fusing of infrared and visible images, the performance of image registration determines whether the two images can be fused at correct spatial position. In the actual scenario, the varied imaging devices may lead to a change in perspective or time gap between shots, making significant non-rigid spatial relationship in infrared and visible images. Even if a large number of feature points are matched, the registration accuracy may still be inadequate, affecting the result of image fusion and other vision tasks. To alleviate this problem, we propose a Semantic-Aware on-Demand registration network (SA-DNet), which mainly purpose is to confine the feature matching process to the semantic region of interest (sROI) by designing semantic-aware module (SAM) and HOL-Deep hybrid matching module (HDM). After utilizing TPS to transform infrared and visible images based on the corresponding feature points in sROI, the registered images are fused using image fusion module (IFM) to achieve a fully functional registration and fusion network. Moreover, we point out that for different demands, this type of approach allows us to select semantic objects for feature matching as needed and accomplishes task-specific registration based on specific requirements. To demonstrate the robustness of SA-DNet for non-rigid distortions, we conduct extensive experiments by comparing SA-DNet with five state-of-the-art infrared and visible image feature matching methods, and the experimental results show that our method adapts better to the presence of non-rigid distortions in the images and provides semantically well-registered images.