Learning to Match Features with Geometry-aware Pooling
文献类型：会议论文
| 作者 | Deng, Jiaxin1,2 ; Yang, Xu1,2; Zheng, Suiwu2,3
|
| 出版日期 | 2023 |
| 会议日期 | 2023-11 |
| 会议地点 | 湖南省长沙市 |
| 英文摘要 | Finding reliable and robust correspondences across images is a fundamental and crucial step for many computer vison tasks, such as 3D-reconstruction and virtual reality. However, previous studies still struggle in challenging cases, including large view changes, repetitive pattern and textureless regions, due to the neglect of geometric constraint in the process of feature encoding. Accordingly, we propose a novel GPMatcher, which is designed to introduce geometric constraints and guidance in the feature encoding process. To achieve this goal, we compute camera poses with the corresponding features in each attention layer and adopt a geometry-aware pooling to reduce the redundant information in the next layer. By these means, an iterative geometry-aware pooing and pose estimation pipeline is constructed, which avoids the updating of redundant feaures and reduces the impact of noise. Experiments conducted on a range of evaluation benchmarks demonstrate that our menthod improves the matching accurary and achieves the state-of-the-art performance. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/56651]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组 多模态人工智能系统全国重点实验室 |
| 作者单位 | 1.University of Chinese Academy of Sciences 2.State Key Laboratory of Multimodal Artificial Intelligence, Institute of Automation, Chinese Academy of Sciences 3.Huizhou Zhongke Advanced Manufacturing Limited Company |
| 推荐引用方式 GB/T 7714 | Deng, Jiaxin,Yang, Xu,Zheng, Suiwu. Learning to Match Features with Geometry-aware Pooling[C]. 见:. 湖南省长沙市. 2023-11. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。