Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.08007 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908647047561216 |
|---|---|
| author | Cao, Yifei Liu, Yu Wang, Guolong Liu, Zhu Wang, Kai Zhang, Xianjie Yu, Jizhe Tu, Xun |
| author_facet | Cao, Yifei Liu, Yu Wang, Guolong Liu, Zhu Wang, Kai Zhang, Xianjie Yu, Jizhe Tu, Xun |
| contents | Egocentric visual query localization is vital for embodied AI and VR/AR, yet remains challenging due to camera motion, viewpoint changes, and appearance variations. We present EAGLE, a novel framework that leverages episodic appearance- and geometry-aware memory to achieve unified 2D-3D visual query localization in egocentric vision. Inspired by avian memory consolidation, EAGLE synergistically integrates segmentation guided by an appearance-aware meta-learning memory (AMM), with tracking driven by a geometry-aware localization memory (GLM). This memory consolidation mechanism, through structured appearance and geometry memory banks, stores high-confidence retrieval samples, effectively supporting both long- and short-term modeling of target appearance variations. This enables precise contour delineation with robust spatial discrimination, leading to significantly improved retrieval accuracy. Furthermore, by integrating the VQL-2D output with a visual geometry grounded Transformer (VGGT), we achieve a efficient unification of 2D and 3D tasks, enabling rapid and accurate back-projection into 3D space. Our method achieves state-ofthe-art performance on the Ego4D-VQ benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08007 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EAGLE: Episodic Appearance- and Geometry-aware Memory for Unified 2D-3D Visual Query Localization in Egocentric Vision Cao, Yifei Liu, Yu Wang, Guolong Liu, Zhu Wang, Kai Zhang, Xianjie Yu, Jizhe Tu, Xun Computer Vision and Pattern Recognition Egocentric visual query localization is vital for embodied AI and VR/AR, yet remains challenging due to camera motion, viewpoint changes, and appearance variations. We present EAGLE, a novel framework that leverages episodic appearance- and geometry-aware memory to achieve unified 2D-3D visual query localization in egocentric vision. Inspired by avian memory consolidation, EAGLE synergistically integrates segmentation guided by an appearance-aware meta-learning memory (AMM), with tracking driven by a geometry-aware localization memory (GLM). This memory consolidation mechanism, through structured appearance and geometry memory banks, stores high-confidence retrieval samples, effectively supporting both long- and short-term modeling of target appearance variations. This enables precise contour delineation with robust spatial discrimination, leading to significantly improved retrieval accuracy. Furthermore, by integrating the VQL-2D output with a visual geometry grounded Transformer (VGGT), we achieve a efficient unification of 2D and 3D tasks, enabling rapid and accurate back-projection into 3D space. Our method achieves state-ofthe-art performance on the Ego4D-VQ benchmark. |
| title | EAGLE: Episodic Appearance- and Geometry-aware Memory for Unified 2D-3D Visual Query Localization in Egocentric Vision |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.08007 |