用几何关系提升跨组位姿估计精度，仅需少量可训练参数。
G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation
- 保留预训练模型不变，新增三个轻量模块建模组内与组间关系。
- 在四个数据集上达到当前最优效果，参数增量不足原模型6%。
- 适合需要低开销跨场景定位的视觉系统开发者使用。
在跨序列重定位和多相机系统里程计中，恢复两组图像间的相对6自由度位姿至关重要。每组图像已知组内几何结构，预训练多视角骨干网络也已将此类几何信息融合进视觉特征。但现有模型将所有视图视为无结构集合，缺乏跨组推理能力。本文提出 ours{}，保持基础模型完全冻结，仅添加三个轻量级可训练模块：感知器重采样器、融合自注意力的跨组桥梁，以及多帧位姿头。总可训练参数约3200万，低于全模型的6%，且仅通过相对位姿进行监督。在涵盖室内外仿真、真实世界跨季节采集及零样本模拟到现实迁移的四个数据集上， ours{} 在两项任务中均取得当前最优性能，且所有基线均以完整原始监督重新训练。代码已开源于 https://github.com/WeiYuFei0217/G2G。
原文摘要 · Abstract (English)
Recovering the relative 6-DoF pose between two image groups underlies cross-sequence relocalization and multi-camera rig odometry. Each group carries known intra-group geometry from visual odometry or rig calibration, and pretrained multi-view backbones already fuse such geometry into visual features. Yet current models treat all views as an unstructured set, leaving cross-group reasoning as the missing piece. We introduce \ours{}, which keeps the foundation model entirely frozen and adds three lightweight trainable modules to bridge the two groups: a perceiver resampler, a cross-group bridge with merged self-attention, and a multi-frame pose head. The trainable footprint totals about 32M parameters, under 6\% of the full model, and is supervised only by relative poses. Across four datasets that span indoor and outdoor simulation, real-world cross-season capture, and zero-shot sim-to-real transfer, \ours{} attains state-of-the-art accuracy on both tasks, while every baseline is retrained with its full original supervision. Code is available at https://github.com/WeiYuFei0217/G2G.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。