Shape-Former: Bridging CNN and Transformer via ShapeConv for multimodal image matching

J Chen, X Chen, S Chen, Y Liu, Y Rao, Y Yang… - Information …, 2023 - Elsevier
As with any data fusion task, the front-end of the pipeline for image fusion, aiming to collect
multitudinous physical properties from multimodal images taken by different types of …

3dregnet: A deep neural network for 3d point registration

GD Pais, S Ramalingam, VM Govindu… - Proceedings of the …, 2020 - openaccess.thecvf.com
We present 3DRegNet, a novel deep learning architecture for the registration of 3D scans.
Given a set of 3D point correspondences, we build a deep neural network to address the …

Samaug: Point prompt augmentation for segment anything model

H Dai, C Ma, Z Yan, Z Liu, E Shi, Y Li, P Shu… - arxiv preprint arxiv …, 2023 - arxiv.org
This paper introduces SAMAug, a novel visual point augmentation method for the Segment
Anything Model (SAM) that enhances interactive image segmentation performance …

Feature dynamic alignment and refinement for infrared–visible image fusion: Translation robust fusion

H Li, J Zhao, J Li, Z Yu, G Lu - Information Fusion, 2023 - Elsevier
Translational displacement between source images from different sensors is a general
phenomenon, which will cause performance degradation on image fusion. To tackle this …

Robust feature matching using spatial clustering with heavy outliers

X Jiang, J Ma, J Jiang, X Guo - IEEE Transactions on Image …, 2019 - ieeexplore.ieee.org
This paper focuses on removing mismatches from given putative feature matches created
typically based on descriptor similarity. To achieve this goal, existing attempts usually …

A two-step descriptor-based keypoint filtering algorithm for robust image matching

V Mousavi, M Varshosaz, F Remondino… - … on Geoscience and …, 2022 - ieeexplore.ieee.org
Finding robust and correct keypoints in images remains a challenge, especially when
repetitive patterns are present. In this article, we propose a universal two-step filtering …