图上下文变换学习用于渐进式对应关系修剪
Graph Context Transformation Learning for Progressive Correspondence Pruning
AI总结：
提出图上下文变换网络GCT-Net，通过增强图上下文并引导共识，实现渐进式对应关系修剪，在离群点移除和相对位姿估计任务上超越现有方法。
摘要：
现有的对应关系修剪方法大多只专注于尽可能多地收集上下文信息，而忽略了利用这些信息的有效方式。为了解决这一困境，本文提出了图上下文变换网络（GCT-Net），通过增强上下文信息来进行共识引导，以实现渐进式对应关系修剪。具体而言，我们设计了图上下文增强变换器，该变换器首先生成图网络，然后将其转换为多分支图上下文。此外，它采用自注意力和交叉注意力来放大每个图上下文的特征，以强调独特且共享的关键信息。为了进一步将重新校准的图上下文应用于全局领域，我们提出了图上下文引导变换器。该模块采用基于置信度的采样策略，临时筛选高置信度顶点，通过搜索筛选顶点与剩余顶点之间的全局共识来引导准确分类。在离群点移除和相对位姿估计上的大量实验结果表明，与现有最先进方法相比，GCT-Net在室外和室内数据集上均展现出优越性能。源代码将在以下网址提供：https://github.com/guobaoxiao/GCT-Net/。
英文摘要：
Most of existing correspondence pruning methods only concentrate on gathering the context information as much as possible while neglecting effective ways to utilize such information. In order to tackle this dilemma, in this paper we propose Graph Context Transformation Network (GCT-Net) enhancing context information to conduct consensus guidance for progressive correspondence pruning. Specifically, we design the Graph Context Enhance Transformer which first generates the graph network and then transforms it into multi-branch graph contexts. Moreover, it employs self-attention and cross-attention to magnify characteristics of each graph context for emphasizing the unique as well as shared essential information. To further apply the recalibrated graph contexts to the global domain, we propose the Graph Context Guidance Transformer. This module adopts a confident-based sampling strategy to temporarily screen high-confidence vertices for guiding accurate classification by searching global consensus between screened vertices and remaining ones. The extensive experimental results on outlier removal and relative pose estimation clearly demonstrate the superior performance of GCT-Net compared to state-of-the-art methods across outdoor and indoor datasets. The source code will be available at: https://github.com/guobaoxiao/GCT-Net/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
