IEEE Transactions on Circuits and Systems for Video Technology / 6D位姿

SceneGlue: Scene-Aware Transformer for Feature Matching without Scene-Level Annotation

作者：Songlin Du, Xiaoyong Lu, Yaping Yan, Guobao Xiao, Xiaobo Lu, Takeshi Ikenaga · 单位：Southeast University, Tongji University, Waseda University · 会议/期刊：IEEE Transactions on Circuits and Systems for Video Technology · 方向：6D位姿 · 发布日期：2026-04-15

6D位姿估计
新标签打开 AlphaXiv新标签打开 Code
SceneGlue: Scene-Aware Transformer for Feature Matching without Scene-Level Annotation figure
AlphaXiv 中文概览（可滚动查看）